© 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. 108934
    Prev
    Next
    INDEX
    Explanations

    references to experts and scholarly opinions

    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
    aft
    -0.07
    ocol
    -0.07
    lue
    -0.07
     ãĢľ
    -0.06
    illet
    -0.06
    лÑİ
    -0.06
    .Hosting
    -0.06
    entina
    -0.06
    êµ´
    -0.06
    ære
    -0.06
    POSITIVE LOGITS
     بÙĪابة
    0.07
    /auth
    0.07
    åĭ
    0.06
    ipment
    0.06
    ãĥ³ãĥIJ
    0.06
     say
    0.06
    .vo
    0.06
    opor
    0.06
     reports
    0.06
    utan
    0.06
    Activations Density 0.025%

    No Known Activations