© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 18545
    Prev
    Next
    INDEX
    Explanations

    terms related to built-in features or components of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "built-in" or "built in" describing integrated features or components.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of built-in or integrated features/components within devices, software, or systems.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.24
    erer
    -0.20
    esthes
    -0.17
    erse
    -0.17
    erate
    -0.16
    343
    -0.15
    _ABI
    -0.14
    одÑĥ
    -0.14
    eter
    -0.14
    nic
    -0.14
    POSITIVE LOGITS
    -in
    0.26
    -for
    0.18
    ins
    0.18
    built
    0.17
    SessionFactory
    0.17
    ingroup
    0.17
    upper
    0.17
    iful
    0.16
     Built
    0.16
    leaning
    0.15
    Activations Density 0.018%

    No Known Activations