© 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. 17-LLAMASCOPE-RES-131K
    11. 118142
    Prev
    Next
    INDEX
    Explanations

    various configuration and option attributes in code

    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
    eniable
    -0.08
    ifton
    -0.07
    ucas
    -0.07
    лиÑĪком
    -0.07
    kins
    -0.06
    EDA
    -0.06
    aeda
    -0.06
    eor
    -0.06
    ysl
    -0.06
    isclosed
    -0.06
    POSITIVE LOGITS
    ÂĿ
    0.07
     />↵
    0.07
    âĢİ
    0.06
    ogany
    0.06
     Demp
    0.06
    essim
    0.06
    linger
    0.06
    urement
    0.06
    anker
    0.06
    [@
    0.06
    Activations Density 0.034%

    No Known Activations