© 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. 71048
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation or critique of media content

    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
     Freeze
    -0.06
    WARE
    -0.06
    rint
    -0.06
    atty
    -0.06
    vn
    -0.06
    ë¡ł
    -0.06
    uitka
    -0.06
     Flux
    -0.06
    .ru
    -0.06
    bons
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥ¼
    0.06
    .synthetic
    0.06
    ij
    0.06
    $MESS
    0.06
     Powers
    0.06
    /Dk
    0.06
    amon
    0.06
    Ĥ
    0.06
    inker
    0.06
     prv
    0.06
    Activations Density 0.007%

    No Known Activations