© 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. 17-LLAMASCOPE-RES-131K
    11. 55470
    Prev
    Next
    INDEX
    Explanations

    function calls and method invocations related to string manipulation and array handling

    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
    leigh
    -0.07
    uen
    -0.07
    utas
    -0.07
    ÄįÃŃ
    -0.07
     bÃŃ
    -0.07
    esting
    -0.07
    tam
    -0.06
    elli
    -0.06
    ë§Ŀ
    -0.06
    buie
    -0.06
    POSITIVE LOGITS
    agos
    0.07
    anel
    0.06
    cribed
    0.06
     oppos
    0.06
     lad
    0.06
    Existing
    0.06
    anca
    0.06
     existing
    0.06
    ibri
    0.06
    ('/',
    0.06
    Activations Density 0.004%

    No Known Activations