© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126998
    Prev
    Next
    INDEX
    Explanations

    programming or code-related comments and documentation

    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
    shal
    -0.08
    ssf
    -0.07
    kaar
    -0.07
    ahoma
    -0.06
     stro
    -0.06
    olare
    -0.06
    //{{
    -0.05
    stk
    -0.05
    uppe
    -0.05
    KeySpec
    -0.05
    POSITIVE LOGITS
    .DropTable
    0.08
    Periph
    0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.07
     Livingston
    0.07
     numberWith
    0.07
    éļ
    0.07
    desc
    0.06
     DESCRIPTION
    0.06
    uitka
    0.06
    Desc
    0.06
    Activations Density 0.009%

    No Known Activations