© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3518
    Prev
    Next
    INDEX
    Explanations

    references to biological growth and characteristics

    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
     hạng
    -0.07
    zung
    -0.06
    odom
    -0.06
    vap
    -0.06
    ç«ł
    -0.06
    _MAJOR
    -0.06
    odata
    -0.06
    adin
    -0.06
     vul
    -0.06
     brains
    -0.06
    POSITIVE LOGITS
     shaft
    0.07
    åij¨æľŁ
    0.07
    HashCode
    0.07
     cycle
    0.07
    帽
    0.07
    ":[{↵
    0.07
    ÑĹв
    0.06
     follic
    0.06
     çĶŁåij½åij¨æľŁ
    0.06
     reim
    0.06
    Activations Density 0.002%

    No Known Activations