© 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. 76414
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or anticipation related to events or gatherings

    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
    ieran
    -0.06
     law
    -0.06
    /stdc
    -0.06
     Grade
    -0.06
     pocket
    -0.06
    foot
    -0.06
     Neg
    -0.06
     performance
    -0.06
     pii
    -0.05
     Tar
    -0.05
    POSITIVE LOGITS
     selv
    0.07
    год
    0.07
     salopes
    0.07
    abus
    0.07
    orex
    0.07
     chá»ĵng
    0.07
    cox
    0.06
     гем
    0.06
     ÑĤвоÑĢ
    0.06
     ÐŁÐ¾Ðº
    0.06
    Activations Density 0.007%

    No Known Activations