© 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. 99258
    Prev
    Next
    INDEX
    Explanations

    references to legal and copyright issues

    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
    lever
    -0.06
    razier
    -0.06
    ernel
    -0.06
    akes
    -0.06
    ram
    -0.06
    aos
    -0.06
     Sle
    -0.05
     Parr
    -0.05
     Sax
    -0.05
    ocity
    -0.05
    POSITIVE LOGITS
    ylon
    0.07
    ennie
    0.07
    δα
    0.07
    à¥įवत
    0.07
    ÎķÎļ
    0.06
    tains
    0.06
    ocalypse
    0.06
    META
    0.06
     util
    0.06
    ONSE
    0.06
    Activations Density 0.002%

    No Known Activations