© 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. 15574
    Prev
    Next
    INDEX
    Explanations

    specific dates and event indicators in a schedule or timetable format

    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
    undo
    -0.08
    ÏĦον
    -0.07
    scoped
    -0.07
    ibbon
    -0.07
    tabl
    -0.07
     PRESS
    -0.07
     BeÅŁ
    -0.07
    ãĤĵãģ©
    -0.06
    нав
    -0.06
    zÄħd
    -0.06
    POSITIVE LOGITS
    orman
    0.06
    iese
    0.06
    ience
    0.06
    iaux
    0.06
    igos
    0.06
    etype
    0.06
    ensing
    0.06
    omes
    0.06
    ll
    0.06
    ĭ
    0.06
    Activations Density 0.046%

    No Known Activations