© 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 EvalsExportsinterp-engineNEWAPI 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. 73463
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or vagueness in statements

    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
    διά
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    manı
    -0.06
    acon
    -0.06
    ยม
    -0.06
    oppel
    -0.06
    опÑĢоÑģ
    -0.06
    алÑĭ
    -0.06
    [:-
    -0.06
     کاÙĦ
    -0.06
    POSITIVE LOGITS
     tiny
    0.20
     small
    0.19
    tiny
    0.15
    -small
    0.15
     SMALL
    0.15
    Tiny
    0.14
    small
    0.14
    Small
    0.14
    å°ı
    0.14
     nhá»ı
    0.14
    Activations Density 0.105%

    No Known Activations