© 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. 40583
    Prev
    Next
    INDEX
    Explanations

    elements related to holiday-themed events in games

    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
     Sanford
    -0.06
    InstanceState
    -0.06
    elopment
    -0.06
    èĪĪ
    -0.06
     almost
    -0.06
     pok
    -0.06
     cena
    -0.06
     convention
    -0.06
    ral
    -0.06
    무
    -0.06
    POSITIVE LOGITS
    AYER
    0.07
    iku
    0.07
    illin
    0.07
    udic
    0.06
     une
    0.06
    special
    0.06
     sarÃł
    0.06
    imest
    0.06
    angelog
    0.06
    cht
    0.06
    Activations Density 0.002%

    No Known Activations