© 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. 121549
    Prev
    Next
    INDEX
    Explanations

    proper names and specific personal identifiers

    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
    ìĦľ
    -0.06
    oids
    -0.06
    ÑĢев
    -0.06
    oid
    -0.06
    geist
    -0.06
    _EXTERN
    -0.06
    eller
    -0.06
     SqlParameter
    -0.06
    uchi
    -0.06
    998
    -0.06
    POSITIVE LOGITS
    cob
    0.08
    rosse
    0.08
    abox
    0.08
    ackers
    0.08
    eer
    0.07
    еÑĢин
    0.07
    obao
    0.07
    DMI
    0.07
    xis
    0.07
     ç¨
    0.07
    Activations Density 0.022%

    No Known Activations