© 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. 124277
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly 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
    ategy
    -0.07
    arpa
    -0.06
    ifecycle
    -0.06
    ÄĽle
    -0.06
    Å¡t
    -0.06
    cmc
    -0.06
    ohana
    -0.06
    PCODE
    -0.06
    minent
    -0.06
     patch
    -0.06
    POSITIVE LOGITS
    vir
    0.07
    anked
    0.06
    èĻ
    0.06
     lại
    0.06
     Crane
    0.06
    agi
    0.06
    otton
    0.06
    ald
    0.06
    odyn
    0.06
     virgin
    0.06
    Activations Density 0.004%

    No Known Activations