© 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. 105939
    Prev
    Next
    INDEX
    Explanations

    references to the word "Dunk" and its various forms or 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
     Quint
    -0.07
     Morrow
    -0.07
    dera
    -0.07
    RIX
    -0.07
    ãĥ¼ãĥį
    -0.07
    ãĤ«ãĥĨ
    -0.06
    gar
    -0.06
    اتÛĮ
    -0.06
    chyb
    -0.06
    acias
    -0.06
    POSITIVE LOGITS
    esco
    0.08
    es
    0.07
    ingly
    0.07
    town
    0.07
    ics
    0.07
    duck
    0.07
    ẩm
    0.06
    ayan
    0.06
    ingu
    0.06
    krom
    0.06
    Activations Density 0.004%

    No Known Activations