© 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. 27100
    Prev
    Next
    INDEX
    Explanations

    events, activities, or gatherings that indicate a sense of celebration or community involvement

    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
    tember
    -0.07
     plá
    -0.07
    rita
    -0.07
    .elem
    -0.07
    ñana
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
     Chic
    -0.06
    urvey
    -0.06
    zew
    -0.06
    chu
    -0.06
    POSITIVE LOGITS
    -style
    0.07
    ulti
    0.07
     INLINE
    0.06
    ist
    0.06
    -esque
    0.06
    ault
    0.06
     lấy
    0.06
    .VK
    0.06
    ingo
    0.06
     Peak
    0.06
    Activations Density 0.034%

    No Known Activations