© 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. 99156
    Prev
    Next
    INDEX
    Explanations

    relationships and consequences in cause-and-effect scenarios

    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
    ITY
    -0.06
    zm
    -0.06
     History
    -0.06
    .utilities
    -0.06
    .GetDirectoryName
    -0.06
    æģµ
    -0.06
     Beau
    -0.06
    umblr
    -0.06
    кÑģ
    -0.06
    ime
    -0.06
    POSITIVE LOGITS
    ardy
    0.07
     곧
    0.07
    thern
    0.07
     âĹĦ
    0.07
    ì£Ħ
    0.06
    kj
    0.06
    hazi
    0.06
    hud
    0.06
     é«
    0.06
    uforia
    0.06
    Activations Density 0.064%

    No Known Activations