© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75300
    Prev
    Next
    INDEX
    Explanations

    mentions of Santa Claus and related holiday themes

    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
    ingly
    -0.07
    edList
    -0.07
    ewolf
    -0.07
    eldon
    -0.06
    elay
    -0.06
    ÙĨÚ¯
    -0.06
    omens
    -0.06
    ÂŃing
    -0.06
    ìĹIJëıĦ
    -0.06
    undy
    -0.06
    POSITIVE LOGITS
     himself
    0.12
     Claus
    0.08
     ÙĨÙ쨳Ùĩ
    0.08
    prene
    0.08
    íĥ
    0.07
    inic
    0.07
    ctica
    0.07
     Himself
    0.07
    brig
    0.06
    ÑĢеп
    0.06
    Activations Density 0.004%

    No Known Activations