© 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. 63058
    Prev
    Next
    INDEX
    Explanations

    instances of physical force or constriction

    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
    zl
    -0.07
    ipur
    -0.07
    inç
    -0.06
    bai
    -0.06
    .nih
    -0.06
    èį
    -0.06
     Heights
    -0.06
    .ev
    -0.06
    cosa
    -0.06
    ame
    -0.06
    POSITIVE LOGITS
     into
    0.10
    oes
    0.09
     vÃło
    0.08
    _into
    0.08
    Into
    0.08
     INTO
    0.08
    into
    0.08
     Into
    0.08
    ovit
    0.08
    -fit
    0.07
    Activations Density 0.014%

    No Known Activations