Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125560
    Prev
    Next
    INDEX
    Explanations

    references to website interactions and user engagement

    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
    jÃŃm
    -0.07
    à¸Ńม
    -0.07
    ụy
    -0.07
    ยา
    -0.06
    aca
    -0.06
    _rhs
    -0.06
    thouse
    -0.06
    lak
    -0.06
    ilee
    -0.06
    RIC
    -0.06
    POSITIVE LOGITS
    quin
    0.07
    rior
    0.07
     ours
    0.07
     Overs
    0.06
    NU
    0.06
     Prior
    0.06
    ARN
    0.06
    æĿ¥çļĦ
    0.06
    oucher
    0.06
    127
    0.06
    Activations Density 0.002%

    No Known Activations