© 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. 9-LLAMASCOPE-RES-131K
    11. 98952
    Prev
    Next
    INDEX
    Explanations

    references to machine learning libraries and data processing frameworks

    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
     Dann
    -0.06
    Ī
    -0.06
    ones
    -0.06
    ov
    -0.06
     sav
    -0.06
    oyal
    -0.06
     multip
    -0.06
    631
    -0.06
    me
    -0.06
    nan
    -0.06
    POSITIVE LOGITS
    esso
    0.08
    edla
    0.07
     оÑĤв
    0.07
    edback
    0.07
     âĹĭ
    0.07
    uitka
    0.07
    ekl
    0.07
    tility
    0.07
    ÑĪов
    0.07
    itos
    0.07
    Activations Density 0.015%

    No Known Activations