© 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. 106686
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in legal or formal documents

    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
    abin
    -0.07
    itan
    -0.06
    .retry
    -0.06
    SEA
    -0.06
     admissions
    -0.06
    bart
    -0.06
    ãĤ¦ãĤ¹
    -0.06
    _BOOT
    -0.06
    ago
    -0.06
    _DST
    -0.06
    POSITIVE LOGITS
     reasoning
    0.07
    asca
    0.07
    ersonic
    0.07
    ãĤ«ãĥĨãĤ´ãĥª
    0.07
    ixe
    0.06
    inaire
    0.06
    orz
    0.06
    gli
    0.06
    elts
    0.06
    PointSize
    0.06
    Activations Density 0.014%

    No Known Activations