© 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. 84674
    Prev
    Next
    INDEX
    Explanations

    variations of the name "McDonald."

    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
    oons
    -0.08
     bom
    -0.07
     ucwords
    -0.07
     Andersen
    -0.06
    imary
    -0.06
    ubl
    -0.06
    toi
    -0.06
    Та
    -0.06
    nts
    -0.06
    obic
    -0.06
    POSITIVE LOGITS
    nell
    0.08
    ellan
    0.08
    an
    0.07
    ãĥ«ãĤ¯
    0.07
    urm
    0.07
    _equals
    0.06
    er
    0.06
    ory
    0.06
    ocator
    0.06
    cert
    0.06
    Activations Density 0.002%

    No Known Activations