© 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. 1241
    Prev
    Next
    INDEX
    Explanations

    topics related to health and societal issues

    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
    angl
    -0.07
    REW
    -0.07
    bara
    -0.07
    akest
    -0.07
    mada
    -0.07
    cente
    -0.07
    ALAR
    -0.07
    ÑģÑĥÑĤ
    -0.07
    AX
    -0.07
    idl
    -0.07
    POSITIVE LOGITS
     actionTypes
    0.07
     success
    0.07
     why
    0.07
     besides
    0.07
    0.06
     Why
    0.06
     observed
    0.06
     phenomenon
    0.06
     Phen
    0.06
     being
    0.06
    Activations Density 0.042%

    No Known Activations