© 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. 69024
    Prev
    Next
    INDEX
    Explanations

    references to deadlines and punctuality in project-related contexts

    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
     Dum
    -0.07
     odd
    -0.06
     Dynam
    -0.06
    į
    -0.06
    èĩ
    -0.06
    us
    -0.06
    to
    -0.06
    omor
    -0.06
     Doch
    -0.06
    wy
    -0.05
    POSITIVE LOGITS
    /on
    0.08
    /at
    0.07
    .btnExit
    0.07
    WithMany
    0.07
    ourcem
    0.07
    ãĥ¬ãĥĵ
    0.07
    otts
    0.06
    太éĥİ
    0.06
    completion
    0.06
    iversal
    0.06
    Activations Density 0.005%

    No Known Activations