© 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. 89857
    Prev
    Next
    INDEX
    Explanations

    specific numeric data and references in text

    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
    .GroupLayout
    -0.07
    392
    -0.07
    ικα
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    FML
    -0.07
    391
    -0.07
     Allan
    -0.06
    åĪij
    -0.06
    .formData
    -0.06
    zon
    -0.06
    POSITIVE LOGITS
    ozem
    0.07
    olut
    0.07
    837
    0.07
    ringe
    0.07
    aptic
    0.06
    rit
    0.06
    jÃł
    0.06
    icense
    0.05
     nad
    0.05
    enders
    0.05
    Activations Density 0.008%

    No Known Activations