© 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. 14176
    Prev
    Next
    INDEX
    Explanations

    web-related technical language, particularly URLs and function calls

    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
    odie
    -0.07
    odate
    -0.06
    ipa
    -0.06
    anding
    -0.06
    Äįky
    -0.06
    ideo
    -0.06
    venes
    -0.06
    odge
    -0.06
     MacDonald
    -0.06
    adera
    -0.06
    POSITIVE LOGITS
    _IOC
    0.07
    shal
    0.07
    .userInteractionEnabled
    0.07
    ฯ
    0.06
    argout
    0.06
    ALES
    0.06
    kits
    0.06
    ãģķãĤĵ
    0.06
    ullo
    0.06
    ALSE
    0.06
    Activations Density 0.098%

    No Known Activations