© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125531
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or questioning knowledge

    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
    uggy
    -0.07
    reau
    -0.07
    åĻ
    -0.07
    ÑģÑĤÑĥп
    -0.07
    retty
    -0.06
    uzzi
    -0.06
    asley
    -0.06
    acie
    -0.06
    ond
    -0.06
    ynes
    -0.06
    POSITIVE LOGITS
     whether
    0.11
     exactly
    0.09
    whether
    0.09
     Whether
    0.09
    æĺ¯åIJ¦
    0.09
     WHETHER
    0.09
     precisely
    0.08
    Whether
    0.08
     exact
    0.07
     nor
    0.07
    Activations Density 0.015%

    No Known Activations