© 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. 106181
    Prev
    Next
    INDEX
    Explanations

    references to "Bul" or related terms, particularly focusing on the context of certain characters or entities

    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
    atas
    -0.07
    bour
    -0.07
    elli
    -0.07
    /LICENSE
    -0.07
    athon
    -0.06
    bsub
    -0.06
    dealloc
    -0.06
    iable
    -0.06
    stå
    -0.06
    erty
    -0.06
    POSITIVE LOGITS
    frog
    0.09
    apest
    0.08
    anza
    0.07
    leted
    0.07
    formed
    0.07
    EMA
    0.07
    monary
    0.06
    èĤ¥
    0.06
    levard
    0.06
    hardt
    0.06
    Activations Density 0.010%

    No Known Activations