© 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. 69331
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ba" and its variations or related forms

    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
    elik
    -0.07
     Vide
    -0.07
    traits
    -0.07
    .subscribe
    -0.07
    usu
    -0.07
    iland
    -0.07
    apper
    -0.07
     Ñĥва
    -0.06
    rans
    -0.06
    еÑĢÑĤа
    -0.06
    POSITIVE LOGITS
    ground
    0.07
    .gdx
    0.07
    onet
    0.06
    FTA
    0.06
    37
    0.06
    utura
    0.06
    38
    0.06
     dep
    0.06
    ister
    0.06
    107
    0.06
    Activations Density 0.030%

    No Known Activations