© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Austin."

    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
    ihan
    -0.08
    lesh
    -0.08
    leen
    -0.08
    licken
    -0.08
    ÑģÑĥÑĤ
    -0.07
    lest
    -0.07
    zcze
    -0.07
    ignment
    -0.07
    lez
    -0.07
    Å¡t
    -0.07
    POSITIVE LOGITS
    adera
    0.07
    liner
    0.07
    mere
    0.06
    ian
    0.06
     TestCase
    0.06
    ampire
    0.06
    ero
    0.06
     Nack
    0.06
    ovy
    0.06
    lime
    0.06
    Activations Density 0.005%

    No Known Activations