© 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. 15-LLAMASCOPE-RES-131K
    11. 103733
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or skepticism about understanding or 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
    osite
    -0.08
    upe
    -0.07
    озв
    -0.07
    óz
    -0.07
    stoff
    -0.07
    Ľ°
    -0.07
     æĥħ
    -0.07
    utdown
    -0.07
    emain
    -0.07
    æĥħ
    -0.06
    POSITIVE LOGITS
    conde
    0.07
     mention
    0.07
     explan
    0.06
    segue
    0.06
    ÙĪÙĬÙĥ
    0.06
     notice
    0.06
     concern
    0.06
    sek
    0.06
    CJK
    0.06
     acknow
    0.06
    Activations Density 0.021%

    No Known Activations