© 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. 103935
    Prev
    Next
    INDEX
    Explanations

    articles referring to a diverse or extensive range of subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    /lic
    -0.08
    /mit
    -0.07
    .Helper
    -0.07
    rung
    -0.07
    ÑĥÑĢн
    -0.07
    stal
    -0.07
    ubic
    -0.07
     Chance
    -0.07
    ùa
    -0.07
     Sized
    -0.07
    POSITIVE LOGITS
     range
    0.12
    range
    0.09
     variety
    0.09
     wide
    0.08
    -range
    0.08
    (range
    0.07
     gam
    0.07
    Range
    0.07
     Range
    0.07
     spectrum
    0.07
    Activations Density 0.010%

    No Known Activations