© 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 EvalsExportsAPI 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. 29006
    Prev
    Next
    INDEX
    Explanations

    occurrences of commas and their context within the text

    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
    (strict
    -0.07
     imagine
    -0.07
    mere
    -0.06
    anco
    -0.06
    046
    -0.06
    azo
    -0.06
    Äĥng
    -0.06
    egr
    -0.06
     true
    -0.06
    cod
    -0.05
    POSITIVE LOGITS
    opies
    0.08
    uch
    0.08
    swagen
    0.07
    acons
    0.07
    بÙĪر
    0.07
    luet
    0.07
    Äįit
    0.07
    stial
    0.07
    yte
    0.07
    estion
    0.06
    Activations Density 0.049%

    No Known Activations