© 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. 104220
    Prev
    Next
    INDEX
    Explanations

    punctuation and specialized terms related to medical conditions or descriptions

    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
     Temp
    -0.06
    templ
    -0.06
    iou
    -0.06
    lobal
    -0.06
     temporal
    -0.06
    kla
    -0.06
    ãĤ¥
    -0.05
    disposed
    -0.05
     Top
    -0.05
    FINAL
    -0.05
    POSITIVE LOGITS
    abinet
    0.08
    Drv
    0.07
    angan
    0.07
    ANJI
    0.07
    awai
    0.07
    _UNUSED
    0.07
    abin
    0.07
    klady
    0.07
    æĦıè§ģ
    0.07
     Fehler
    0.07
    Activations Density 0.001%

    No Known Activations