© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92279
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    tie
    -0.07
    /inet
    -0.07
     sometimes
    -0.07
    uche
    -0.07
    á»ĵn
    -0.07
    sey
    -0.06
    .scalablytyped
    -0.06
    unker
    -0.06
    imore
    -0.06
    mund
    -0.06
    POSITIVE LOGITS
     else
    0.12
    _else
    0.10
    else
    0.09
    278
    0.08
    Else
    0.08
    ewhere
    0.07
    451
    0.07
    facility
    0.07
    nex
    0.07
    adow
    0.07
    Activations Density 0.003%

    No Known Activations