© 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. 56516
    Prev
    Next
    INDEX
    Explanations

    scientific classification and descriptions of organisms

    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
    tréal
    -0.07
    cells
    -0.07
    #ab
    -0.07
    γκα
    -0.07
     Cells
    -0.07
    _cells
    -0.07
    .sessions
    -0.07
    /stats
    -0.07
     æ½
    -0.07
    legacy
    -0.07
    POSITIVE LOGITS
    \↵
    0.06
     Gri
    0.06
    eral
    0.06
     wider
    0.06
     substr
    0.06
     Singleton
    0.06
    ocrates
    0.05
     subs
    0.05
     transcript
    0.05
    emens
    0.05
    Activations Density 0.006%

    No Known Activations