© 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. 125942
    Prev
    Next
    INDEX
    Explanations

    references to voting or selections within the context of events or competitions

    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
     -*-č↵
    -0.08
    @author
    -0.07
    èĥŀ
    -0.07
    hausen
    -0.07
    atti
    -0.07
    /bind
    -0.07
    sono
    -0.07
     KiÅŁ
    -0.07
    è§Ī
    -0.07
     имÑĥ
    -0.07
    POSITIVE LOGITS
     favorite
    0.09
     favourite
    0.09
     Favorite
    0.08
     vote
    0.07
    arat
    0.07
     Vote
    0.07
    vote
    0.07
    favorite
    0.07
    Favorite
    0.07
    Vote
    0.06
    Activations Density 0.007%

    No Known Activations