© 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. 60830
    Prev
    Next
    INDEX
    Explanations

    JavaScript-related code or functions, particularly those dealing with HTTP requests and responses

    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
    uci
    -0.07
    erial
    -0.07
     radi
    -0.06
    akes
    -0.06
     mobil
    -0.06
     dro
    -0.06
    atum
    -0.06
    azaar
    -0.05
    pz
    -0.05
    173
    -0.05
    POSITIVE LOGITS
    ίνα
    0.09
    gebn
    0.08
    Æ¡
    0.07
    ogui
    0.07
     Headers
    0.07
    _headers
    0.07
    AnimationFrame
    0.07
     HEAD
    0.07
    _LAYER
    0.07
    _BINARY
    0.07
    Activations Density 0.003%

    No Known Activations