© 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. 95868
    Prev
    Next
    INDEX
    Explanations

    disclaimers and statements about medical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    kea
    -0.06
    oon
    -0.06
    -utils
    -0.06
     Paperback
    -0.06
     fres
    -0.06
    etz
    -0.06
    zÃŃ
    -0.05
    zem
    -0.05
    olly
    -0.05
     INCIDENT
    -0.05
    POSITIVE LOGITS
    egr
    0.07
    icals
    0.07
    idl
    0.07
     alphabet
    0.06
     Gund
    0.06
    ampire
    0.06
    CHASE
    0.06
    ships
    0.06
    apers
    0.06
     congest
    0.06
    Activations Density 0.003%

    No Known Activations