© 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. 60751
    Prev
    Next
    INDEX
    Explanations

    programming functions and their declarations

    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
    _stylesheet
    -0.07
    tec
    -0.06
     Wyn
    -0.06
    /npm
    -0.06
    /libs
    -0.06
     Baron
    -0.06
     kiến
    -0.06
    arry
    -0.06
     archit
    -0.06
    ató
    -0.06
    POSITIVE LOGITS
     clone
    0.07
     toString
    0.07
    layan
    0.07
     clones
    0.07
    clone
    0.07
    _clone
    0.07
    HashCode
    0.07
    pretty
    0.06
    toString
    0.06
     Pretty
    0.06
    Activations Density 0.037%

    No Known Activations