© 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. 74689
    Prev
    Next
    INDEX
    Explanations

    HTML elements and metadata related to web documents

    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
    yn
    -0.07
    IRON
    -0.07
    opp
    -0.06
    iban
    -0.06
    iron
    -0.06
    raj
    -0.06
    ond
    -0.06
    _hosts
    -0.06
     Prosper
    -0.05
    à¥Īय
    -0.05
    POSITIVE LOGITS
    san
    0.07
     href
    0.07
    égor
    0.07
    sj
    0.07
    AreaView
    0.06
    OLOR
    0.06
    aje
    0.06
    mast
    0.06
     ëª
    0.06
     sanct
    0.06
    Activations Density 0.002%

    No Known Activations