© 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. 108959
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases indicating inclusivity or additional information

    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
    ainless
    -0.07
    solete
    -0.06
    alyzer
    -0.06
    tains
    -0.06
    enze
    -0.06
    ToFit
    -0.06
    CreatedBy
    -0.06
    Ñĩай
    -0.06
    iless
    -0.06
    ÃŃny
    -0.06
    POSITIVE LOGITS
    usive
    0.07
    clusive
    0.07
    IAL
    0.07
    igator
    0.06
    ighter
    0.06
     Orr
    0.06
    UPI
    0.06
    zero
    0.06
    .Framework
    0.06
    .MixedReality
    0.06
    Activations Density 0.002%

    No Known Activations