© 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. 121511
    Prev
    Next
    INDEX
    Explanations

    items or elements listed in a sequence

    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
    aring
    -0.07
     hem
    -0.06
    AffineTransform
    -0.06
    Finished
    -0.06
    257
    -0.06
    olley
    -0.06
    uble
    -0.06
    uggle
    -0.06
     Finished
    -0.06
     bar
    -0.06
    POSITIVE LOGITS
    avax
    0.08
    %X
    0.07
    /YYYY
    0.07
     Kale
    0.07
    dna
    0.07
     éĵ
    0.07
    trx
    0.07
    mint
    0.06
    .daily
    0.06
    Slinky
    0.06
    Activations Density 0.001%

    No Known Activations