© 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. 60988
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags used for navigation links

    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
    .pix
    -0.07
    vard
    -0.06
    wer
    -0.06
    ako
    -0.06
    ille
    -0.06
    ress
    -0.06
    ãģ£ãģ¡
    -0.06
    éIJĺ
    -0.06
    beth
    -0.06
    embre
    -0.06
    POSITIVE LOGITS
     câ
    0.07
    xies
    0.07
    udic
    0.06
    hazi
    0.06
    FormattedMessage
    0.06
    ski
    0.06
     Walters
    0.06
    elif
    0.06
    IMIT
    0.06
     Booth
    0.06
    Activations Density 0.008%

    No Known Activations