© 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. 85156
    Prev
    Next
    INDEX
    Explanations

    the word "sure" indicating certainty or assurance in various contexts

    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
    olo
    -0.07
    utz
    -0.07
    ãĥ³ãĥĦ
    -0.07
    nat
    -0.06
    oto
    -0.06
    aur
    -0.06
    gos
    -0.06
    ryn
    -0.06
     Fortune
    -0.06
     wooded
    -0.06
    POSITIVE LOGITS
     to
    0.09
    919
    0.06
    tright
    0.06
    pitch
    0.06
    519
    0.06
     misc
    0.06
    Sure
    0.06
    Trip
    0.06
     Sure
    0.06
    ÏĦί
    0.06
    Activations Density 0.003%

    No Known Activations