Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 20853
    Prev
    Next
    INDEX
    Explanations

    patterns related to sports scores or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _stub
    -0.16
    YM
    -0.14
    QRST
    -0.14
    geries
    -0.14
    .dylib
    -0.14
    rier
    -0.14
    ÃŃÅĻ
    -0.13
    tera
    -0.13
    AMESPACE
    -0.13
    PTY
    -0.13
    POSITIVE LOGITS
    anten
    0.16
    apis
    0.16
    ENDED
    0.14
    اÛĮØ´
    0.14
    zek
    0.14
    uter
    0.14
    awi
    0.14
    ouv
    0.14
    avel
    0.13
    avad
    0.13
    Activations Density 0.001%

    No Known Activations