© 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. 61867
    Prev
    Next
    INDEX
    Explanations

    references to tarot card readings and their interpretations

    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
     huy
    -0.08
    íĵ¨
    -0.07
    ź
    -0.07
    bid
    -0.07
    ambi
    -0.07
    енз
    -0.06
    KIT
    -0.06
     duty
    -0.06
    ض
    -0.06
    assen
    -0.06
    POSITIVE LOGITS
    tam
    0.08
     cards
    0.07
    acement
    0.06
     éĢļ
    0.06
     Agricult
    0.06
     card
    0.06
     ÑģÑħод
    0.06
    ificate
    0.06
    teenth
    0.06
    éĥ
    0.06
    Activations Density 0.004%

    No Known Activations