© 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. 26865
    Prev
    Next
    INDEX
    Explanations

    aspects of personal preference and 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
    ergy
    -0.07
    angl
    -0.07
    schemas
    -0.07
    kehr
    -0.06
    ylland
    -0.06
    @↵
    -0.06
    Ĩ
    -0.06
     Actor
    -0.06
    uur
    -0.06
    Pieces
    -0.06
    POSITIVE LOGITS
    atron
    0.07
    ozor
    0.07
     sectional
    0.06
    &S
    0.06
    uby
    0.06
    bons
    0.06
    stroy
    0.06
     practical
    0.06
     Duch
    0.06
    ħ
    0.06
    Activations Density 0.001%

    No Known Activations