© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103428
    Prev
    Next
    INDEX
    Explanations

    instances of special characters or punctuation marks

    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
    erm
    -0.09
    ful
    -0.08
    ses
    -0.07
    arde
    -0.07
    itere
    -0.07
    ible
    -0.06
    pipe
    -0.06
    our
    -0.06
    ourd
    -0.06
    ons
    -0.06
    POSITIVE LOGITS
    o
    0.08
    ï¸ı
    0.07
    339
    0.07
    mpp
    0.07
    zÃŃ
    0.07
    ecko
    0.07
    ا
    0.07
    *>
    0.07
    ught
    0.07
    zan
    0.06
    Activations Density 0.040%

    No Known Activations