© 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. 72086
    Prev
    Next
    INDEX
    Explanations

    the presence of periods indicating the end of statements or thoughts

    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
    vertis
    -0.07
     Pur
    -0.07
    loon
    -0.07
    _UT
    -0.07
    ÙĪرÙĨ
    -0.07
    furt
    -0.06
     resid
    -0.06
    gers
    -0.06
     zel
    -0.06
    ONG
    -0.06
    POSITIVE LOGITS
    ervo
    0.08
    erv
    0.06
    unting
    0.06
    elter
    0.06
    enga
    0.06
    hue
    0.06
    inski
    0.06
     Arap
    0.06
    elocity
    0.06
    (reason
    0.06
    Activations Density 0.000%

    No Known Activations