© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    references to tarot cards and their significance in personal reflection and decision-making

    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
     kilograms
    -0.06
     Reporting
    -0.05
     reporting
    -0.05
    ãģĭãģĦ
    -0.05
    段
    -0.05
     grade
    -0.05
     ç§ij
    -0.05
     Arrow
    -0.05
    arma
    -0.05
    Tail
    -0.05
    POSITIVE LOGITS
     cards
    0.11
     card
    0.09
    cards
    0.08
    .cards
    0.08
     Cards
    0.08
     decks
    0.08
    Cards
    0.08
     amat
    0.08
    (cards
    0.08
    abase
    0.07
    Activations Density 0.007%

    No Known Activations