© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 26591
    Prev
    Next
    INDEX
    Explanations

    general concepts related to significant change or new ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Julian
    -0.15
    angered
    -0.15
    hazi
    -0.14
    .Undef
    -0.14
    laÄį
    -0.14
    .xz
    -0.14
     Roths
    -0.13
    adius
    -0.13
     Leslie
    -0.13
    çħĻ
    -0.13
    POSITIVE LOGITS
    arda
    0.17
     hạ
    0.15
     aim
    0.14
     LGPL
    0.14
    cepts
    0.14
    AttributeValue
    0.14
    viders
    0.13
    655
    0.13
     measured
    0.13
    lu
    0.13
    Activations Density 0.669%

    No Known Activations