© 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. 29660
    Prev
    Next
    INDEX
    Explanations

    mentions of events or items related to Halloween and technological products

    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
    UNCH
    -0.07
    edik
    -0.07
    155
    -0.07
    ÌĨ
    -0.07
    æ´
    -0.07
     ðŁĺī↵↵
    -0.07
    IRST
    -0.07
    emouth
    -0.07
    ://
    -0.07
    łéĻ¤
    -0.07
    POSITIVE LOGITS
    egin
    0.07
    cherche
    0.06
    razier
    0.06
    Lorem
    0.06
     beginnings
    0.06
     update
    0.06
    ptest
    0.06
     another
    0.06
     اÙĦاع
    0.06
    ledged
    0.05
    Activations Density 0.018%

    No Known Activations