© 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. 87488
    Prev
    Next
    INDEX
    Explanations

    conditional statements and instances of uncertainty or speculation

    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
    ãĥ«ãĤ¯
    -0.07
    iem
    -0.07
    ,...↵↵
    -0.07
    ibus
    -0.07
    veau
    -0.07
    Ñģе
    -0.07
    ÅĻez
    -0.07
    IOR
    -0.06
    anzi
    -0.06
     interes
    -0.06
    POSITIVE LOGITS
     unless
    0.13
    unless
    0.12
     Unless
    0.10
    Unless
    0.08
     nor
    0.08
     Ø¥ÙĦا
    0.07
    nor
    0.07
     anymore
    0.06
    arto
    0.06
     until
    0.06
    Activations Density 0.026%

    No Known Activations