© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83614
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical or programming symbols indicating a function or operation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibri
    -0.07
    cip
    -0.07
    spell
    -0.07
    à¥
    -0.06
    icit
    -0.06
    mite
    -0.06
    _continuous
    -0.06
    ãĥIJãĤ¤
    -0.06
     scept
    -0.06
    ODO
    -0.06
    POSITIVE LOGITS
    _Of
    0.06
     yards
    0.06
    port
    0.06
     Fut
    0.06
    ovat
    0.06
    çĬ¬
    0.06
     fut
    0.06
     Coc
    0.06
    Framework
    0.06
     Herb
    0.06
    Activations Density 0.000%

    No Known Activations