© 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. 17-LLAMASCOPE-RES-131K
    11. 56248
    Prev
    Next
    INDEX
    Explanations

    function calls and relational operations in programming contexts

    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
    ána
    -0.08
    /lg
    -0.07
    aho
    -0.07
    rý
    -0.07
    ennen
    -0.07
    ään
    -0.07
    [OF
    -0.07
    RTL
    -0.07
    osg
    -0.07
    WhiteSpace
    -0.07
    POSITIVE LOGITS
    t
    0.06
    adio
    0.06
    éĭ
    0.06
    ilar
    0.06
    in
    0.06
    ro
    0.05
    eph
    0.05
     stand
    0.05
    cht
    0.05
     Kramer
    0.05
    Activations Density 0.002%

    No Known Activations