© 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. 60781
    Prev
    Next
    INDEX
    Explanations

    punctuation and words related to uncertainty or contradiction

    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
    ZR
    -0.07
     Farr
    -0.07
     cest
    -0.07
     ÑģооÑĤвеÑĤ
    -0.07
    lli
    -0.07
    aille
    -0.07
     zwar
    -0.07
    åŃĺäºİ
    -0.07
    å½ĵçĦ¶
    -0.06
    ستر
    -0.06
    POSITIVE LOGITS
     still
    0.13
    still
    0.12
     somehow
    0.12
    noch
    0.11
     nevertheless
    0.11
     Still
    0.11
     STILL
    0.11
     nonetheless
    0.11
    è¿ĺæĺ¯
    0.10
    Still
    0.10
    Activations Density 0.067%

    No Known Activations