© 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. 17819
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    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
     articles
    -0.07
     journal
    -0.07
     journals
    -0.07
    à¸Ĺาà¸ĩ
    -0.07
     article
    -0.07
     Journal
    -0.07
    ResourceId
    -0.07
    204
    -0.06
    ega
    -0.06
    å®ĭä½ĵ
    -0.06
    POSITIVE LOGITS
     book
    0.10
     chapters
    0.10
     chapter
    0.10
    APTER
    0.09
     Chapter
    0.09
     Chapters
    0.09
    chapter
    0.09
    Chapter
    0.08
    -book
    0.08
    book
    0.08
    Activations Density 0.000%

    No Known Activations