© 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. 123609
    Prev
    Next
    INDEX
    Explanations

    references to licensing and copyright information

    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
    exampleInputEmail
    -0.06
    es
    -0.06
    uffman
    -0.06
    olini
    -0.06
    ureau
    -0.06
    exampleInput
    -0.06
    inox
    -0.06
    omens
    -0.06
    erre
    -0.06
     avant
    -0.06
    POSITIVE LOGITS
    utsch
    0.07
    æ¢Ŀ
    0.07
    ãĥ¼ãĥį
    0.07
    alue
    0.07
    Justin
    0.07
     shemale
    0.07
    .struts
    0.07
     lawy
    0.06
    ../../../../
    0.06
    ä½Ļ
    0.06
    Activations Density 0.002%

    No Known Activations