© 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. 31687
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and periods

    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
    ếp
    -0.07
    иÑī
    -0.07
    .scalablytyped
    -0.07
    _OCCURRED
    -0.07
    -être
    -0.07
    mie
    -0.07
    hq
    -0.07
    Ïĥμα
    -0.06
    asons
    -0.06
    359
    -0.06
    POSITIVE LOGITS
    ¦
    0.08
    Ë
    0.06
    lt
    0.06
    resi
    0.06
    ÂĢÂĻ
    0.06
    gether
    0.06
    ernes
    0.06
    ches
    0.06
    ndo
    0.06
    inel
    0.06
    Activations Density 0.069%

    No Known Activations