© 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. 27077
    Prev
    Next
    INDEX
    Explanations

    content related to events and gatherings, particularly those involving food and social interaction

    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
     Viv
    -0.09
     mest
    -0.07
    uzz
    -0.06
    oya
    -0.06
     cle
    -0.06
     Merc
    -0.05
    igor
    -0.05
     Peek
    -0.05
     Organizer
    -0.05
    anka
    -0.05
    POSITIVE LOGITS
    /feed
    0.08
    feed
    0.08
     Ñĥгл
    0.08
    fuel
    0.08
    hape
    0.08
     mouths
    0.07
    -feed
    0.07
     Portions
    0.07
    preferences
    0.07
     sust
    0.07
    Activations Density 0.070%

    No Known Activations