© 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. 80151
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence delimiters 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
    ilename
    -0.06
    flu
    -0.06
    IJëĭ¤
    -0.06
    ün
    -0.06
    _ERR
    -0.06
    tran
    -0.06
    ilter
    -0.06
    iyat
    -0.06
    apixel
    -0.06
     Singer
    -0.06
    POSITIVE LOGITS
     CONTRIBUTORS
    0.07
    essay
    0.06
     Booker
    0.06
    cause
    0.06
    nez
    0.06
    ATALOG
    0.06
    éħ¸
    0.06
     Hob
    0.06
    acos
    0.06
    -ie
    0.06
    Activations Density 0.001%

    No Known Activations