© 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. 38399
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associated actions or states

    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
    chter
    -0.07
    otton
    -0.07
     Brill
    -0.07
    ignite
    -0.07
    _Y
    -0.07
    .scal
    -0.06
    eron
    -0.06
    Ñİн
    -0.06
    afka
    -0.06
    ford
    -0.06
    POSITIVE LOGITS
     thereby
    0.10
    thumb
    0.08
    cci
    0.06
     ensured
    0.06
    еко
    0.06
    amo
    0.06
    моÑģ
    0.06
    è²¼
    0.06
    onga
    0.06
    LOT
    0.06
    Activations Density 0.050%

    No Known Activations