© 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. 57555
    Prev
    Next
    INDEX
    Explanations

    mentions of "rice" and related terms

    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
    acity
    -0.08
    ship
    -0.08
    most
    -0.07
    ry
    -0.07
    name
    -0.07
    ize
    -0.07
    tring
    -0.07
    TRAN
    -0.07
    so
    -0.06
    trans
    -0.06
    POSITIVE LOGITS
    pond
    0.08
    -paper
    0.08
    andler
    0.08
    etti
    0.07
    ermen
    0.07
    aukee
    0.07
    paper
    0.07
     verm
    0.07
    field
    0.07
    gow
    0.07
    Activations Density 0.009%

    No Known Activations