© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and precautionary measures

    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
    ycler
    -0.07
     deep
    -0.06
     prim
    -0.06
    óż
    -0.06
    _deep
    -0.06
    dbg
    -0.06
     franchise
    -0.06
    emd
    -0.06
    deep
    -0.06
     ready
    -0.06
    POSITIVE LOGITS
     wind
    0.13
     gust
    0.12
     winds
    0.12
    wind
    0.10
     Winds
    0.09
    é£İ
    0.09
    _wind
    0.09
    .wind
    0.09
    -force
    0.08
     Wind
    0.08
    Activations Density 0.000%

    No Known Activations