© 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. 26853
    Prev
    Next
    INDEX
    Explanations

    references to web pages or online content creation

    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
    cky
    -0.08
    edla
    -0.07
    enga
    -0.07
    .med
    -0.06
    omo
    -0.06
    atar
    -0.06
    amar
    -0.06
    appa
    -0.06
    Å¡t
    -0.06
    unny
    -0.06
    POSITIVE LOGITS
     Nack
    0.07
    Doctrine
    0.06
    ashes
    0.06
     :+:
    0.06
     Roland
    0.06
    ÑĢÑı
    0.06
    ash
    0.06
    aan
    0.06
    spect
    0.06
    .Aggressive
    0.06
    Activations Density 0.000%

    No Known Activations