© 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. 59011
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their placement in sentences

    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
    ingham
    -0.07
    ses
    -0.07
    rende
    -0.06
    IJëĭ¤
    -0.06
    abay
    -0.06
    sel
    -0.06
    ORMAT
    -0.06
    asted
    -0.06
    oldem
    -0.06
    ÑĪиÑģÑĮ
    -0.06
    POSITIVE LOGITS
    eks
    0.07
    vore
    0.07
    TPL
    0.07
    ityEngine
    0.07
    ãĢħ
    0.06
    ÏħÏĩ
    0.06
    cstdint
    0.06
    olo
    0.06
    ogui
    0.06
    thro
    0.06
    Activations Density 0.056%

    No Known Activations