© 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. 9-LLAMASCOPE-RES-131K
    11. 99007
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to warranties and liabilities

    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
    hower
    -0.07
    uffy
    -0.07
    zcze
    -0.07
    exampleInput
    -0.07
    exampleInputEmail
    -0.07
    ingu
    -0.07
    lyph
    -0.07
    otts
    -0.06
     forControlEvents
    -0.06
    ationToken
    -0.06
    POSITIVE LOGITS
    ideshow
    0.06
    ÑĪе
    0.06
     Able
    0.06
     Cle
    0.06
     stom
    0.06
    _RT
    0.05
    -caret
    0.05
    .rt
    0.05
     Acid
    0.05
     Dort
    0.05
    Activations Density 0.000%

    No Known Activations