© 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. 119805
    Prev
    Next
    INDEX
    Explanations

    keywords related to decision-making and caution in problem-solving

    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
    anela
    -0.08
    ews
    -0.06
     Stan
    -0.06
     Credits
    -0.06
    usu
    -0.06
    136
    -0.06
    574
    -0.06
    .pg
    -0.06
     Gregory
    -0.06
     credits
    -0.06
    POSITIVE LOGITS
     artificial
    0.07
     simply
    0.07
     blindly
    0.07
     sake
    0.07
    Fake
    0.07
    echa
    0.06
    ajor
    0.06
    ink
    0.06
     unless
    0.06
     Artificial
    0.06
    Activations Density 0.028%

    No Known Activations