© 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. 94245
    Prev
    Next
    INDEX
    Explanations

    descriptions of eerie or ghostly imagery

    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
     ê
    -0.07
    addock
    -0.07
    _ASM
    -0.07
    andest
    -0.07
     Favorites
    -0.07
    Ãłng
    -0.06
    êµ´
    -0.06
    razier
    -0.06
    ë¹Ļ
    -0.06
     disposit
    -0.06
    POSITIVE LOGITS
    anes
    0.08
    ply
    0.06
     IMPLIED
    0.06
     ;č↵
    0.06
    ials
    0.06
     Spray
    0.06
     Perkins
    0.06
    oret
    0.06
    isons
    0.06
    atron
    0.06
    Activations Density 0.011%

    No Known Activations