© 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. 39030
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in context

    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
    lesi
    -0.07
     UNUSED
    -0.07
    ëŀ
    -0.07
    hani
    -0.07
     instead
    -0.07
     Moor
    -0.07
    eliac
    -0.07
    ÑĢиÑĤи
    -0.07
    |int
    -0.07
    دÛĮگر
    -0.07
    POSITIVE LOGITS
     whichever
    0.16
     alike
    0.12
     latter
    0.12
     respectively
    0.11
     depending
    0.11
    ichever
    0.11
     Either
    0.10
    depending
    0.10
    Either
    0.10
     either
    0.09
    Activations Density 0.082%

    No Known Activations