© 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. 123429
    Prev
    Next
    INDEX
    Explanations

    expressions related to dialogue and conversational interactions

    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
    lop
    -0.07
    ãģĤãģĤ
    -0.07
    asan
    -0.07
    igh
    -0.06
     REPLACE
    -0.06
    gew
    -0.06
    cott
    -0.06
    arga
    -0.06
    åł´åIJĪ
    -0.06
    etak
    -0.06
    POSITIVE LOGITS
     tell
    0.07
    tell
    0.07
     Did
    0.07
    .are
    0.07
     what
    0.06
     How
    0.06
     did
    0.06
     how
    0.06
     qué
    0.06
     question
    0.06
    Activations Density 0.065%

    No Known Activations