© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104175
    Prev
    Next
    INDEX
    Explanations

    descriptions of adventurous activities and experiences

    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
    indre
    -0.06
    erin
    -0.06
    gard
    -0.06
    Lens
    -0.06
     Wrapped
    -0.06
     value
    -0.06
    аниÑĨ
    -0.06
    ahl
    -0.06
     itemprop
    -0.06
    èĭ
    -0.06
    POSITIVE LOGITS
     contr
    0.07
    Seats
    0.07
     seats
    0.06
    312
    0.06
    prototype
    0.06
    Ïĥκε
    0.06
    riel
    0.06
    ivot
    0.06
     Seats
    0.06
     prototype
    0.06
    Activations Density 0.043%

    No Known Activations