© 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. 104974
    Prev
    Next
    INDEX
    Explanations

    punctuation that signifies character dialogue or quotations

    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
    /or
    -0.09
    ãģįãģŁ
    -0.08
    ÃŃs
    -0.07
    ago
    -0.07
    -caret
    -0.06
    ilis
    -0.06
    spacer
    -0.06
    STR
    -0.06
    dera
    -0.06
    ww
    -0.06
    POSITIVE LOGITS
    ÂĿ
    0.16
    ed
    0.10
    ÛĮ
    0.10
    i
    0.09
    nbsp
    0.08
    ãĢģ“
    0.08
    ़
    0.08
    ãĤĪãģĨãģª
    0.07
    s
    0.07
    -than
    0.07
    Activations Density 0.028%

    No Known Activations