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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 17913
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate sequencing or referencing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omes
    -0.15
    ëį°ìĿ´íĬ¸
    -0.15
    ornado
    -0.14
    пиÑģ
    -0.14
     spinning
    -0.14
    enses
    -0.14
    AtPath
    -0.14
    reshold
    -0.13
    ense
    -0.13
     lane
    -0.13
    POSITIVE LOGITS
    erer
    0.15
    âĶĺ
    0.14
    675
    0.14
    .myapplication
    0.14
    aporation
    0.14
    .elementAt
    0.13
    713
    0.13
    ests
    0.13
    fect
    0.13
    .uni
    0.13
    Activations Density 0.149%

    No Known Activations