© 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. 15-LLAMASCOPE-RES-131K
    11. 61712
    Prev
    Next
    INDEX
    Explanations

    instances of function definitions in code

    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
     submodule
    -0.06
    anus
    -0.06
    lycer
    -0.06
    ÙĨت
    -0.06
    onda
    -0.06
    meli
    -0.06
    rocess
    -0.06
    ette
    -0.06
    roupon
    -0.06
    obia
    -0.06
    POSITIVE LOGITS
    undle
    0.06
    ysize
    0.06
    engo
    0.06
    horse
    0.06
    agli
    0.06
    jer
    0.06
    à¹Ģ
    0.06
    ¸
    0.06
    .obtain
    0.06
     Orr
    0.06
    Activations Density 0.001%

    No Known Activations