© 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. 15-LLAMASCOPE-RES-131K
    11. 90038
    Prev
    Next
    INDEX
    Explanations

    advice related to child safety and supervision

    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
    porto
    -0.07
    duino
    -0.07
    ozor
    -0.07
    ajs
    -0.07
     док
    -0.07
    ãĤ¤ãĤ¯
    -0.07
    ç¨
    -0.07
    ursal
    -0.07
    iena
    -0.06
    sert
    -0.06
    POSITIVE LOGITS
     Scan
    0.07
    awah
    0.06
     sober
    0.06
    ิว
    0.06
    iloc
    0.06
    hir
    0.06
     trailing
    0.06
    ãģ¨ãģĨ
    0.06
    ystack
    0.06
    Scan
    0.05
    Activations Density 0.015%

    No Known Activations