© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106492
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Brook"

    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
     Voj
    -0.07
    ког
    -0.07
    ergus
    -0.07
    ëł¥
    -0.07
    Ùħا
    -0.07
    ãĤ¢ãĥ¼
    -0.07
    APPER
    -0.06
    WithEmail
    -0.06
    iques
    -0.06
    ennon
    -0.06
    POSITIVE LOGITS
    house
    0.08
    shire
    0.07
    dale
    0.07
    omo
    0.07
    ozilla
    0.07
    age
    0.06
     Barg
    0.06
     Pound
    0.06
    eshire
    0.06
    campo
    0.06
    Activations Density 0.008%

    No Known Activations