© 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. 121318
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    κÎŃ
    -0.06
    /to
    -0.06
     "
    -0.06
    aida
    -0.06
    ids
    -0.06
     padd
    -0.06
     vested
    -0.06
    ixo
    -0.06
    LL
    -0.06
     Wolfe
    -0.06
    POSITIVE LOGITS
    ERRU
    0.07
    tring
    0.07
    ãĥĥãĤ°
    0.07
    enge
    0.07
    ORG
    0.06
    çīĩ
    0.06
     Rosenstein
    0.06
    ojis
    0.06
    ujet
    0.06
    ondere
    0.06
    Activations Density 0.007%

    No Known Activations