© 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. 89821
    Prev
    Next
    INDEX
    Explanations

    references to human experiences and personal reflections

    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
    raisal
    -0.09
    QL
    -0.07
    ÄIJT
    -0.07
    recated
    -0.07
    htags
    -0.07
     Jarvis
    -0.07
    ’ÑĶ
    -0.07
    à¥įरम
    -0.06
     Kostenlos
    -0.06
    .UnitTesting
    -0.06
    POSITIVE LOGITS
    bidden
    0.10
    nger
    0.09
    gether
    0.08
    itionally
    0.08
    .wikipedia
    0.07
    bsites
    0.07
    iali
    0.07
    :///
    0.07
    nbsp
    0.07
    ·
    0.07
    Activations Density 0.320%

    No Known Activations