© 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. 5995
    Prev
    Next
    INDEX
    Explanations

    expressions of joy and happiness

    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
    xing
    -0.06
     jud
    -0.06
    OOM
    -0.06
     aw
    -0.06
    moon
    -0.06
    MOVE
    -0.06
    _timezone
    -0.06
    uring
    -0.06
    podob
    -0.06
     GetType
    -0.06
    POSITIVE LOGITS
    fully
    0.11
    fulness
    0.11
    FUL
    0.11
    FULL
    0.10
    full
    0.09
    ful
    0.09
    ride
    0.09
    ably
    0.08
    ous
    0.08
    odel
    0.07
    Activations Density 0.008%

    No Known Activations