© 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. 9-LLAMASCOPE-RES-131K
    11. 99160
    Prev
    Next
    INDEX
    Explanations

    technical document structure elements and metadata

    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
     Fresh
    -0.07
     cultures
    -0.07
     tended
    -0.06
    cai
    -0.06
    ndon
    -0.06
     fresh
    -0.06
    Fresh
    -0.05
    patible
    -0.05
     visible
    -0.05
     culture
    -0.05
    POSITIVE LOGITS
    abis
    0.08
    onet
    0.07
    fos
    0.07
    anger
    0.07
    ãĥ³ãĥģ
    0.07
    /entity
    0.07
    .Console
    0.07
    _rwlock
    0.07
    _corners
    0.07
    ãĥ³ãĥĦ
    0.07
    Activations Density 0.007%

    No Known Activations