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

    Neuronpedia

    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. 87057
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bust" and its variations

    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
    hab
    -0.07
    ertz
    -0.07
    ately
    -0.07
    ials
    -0.07
    387
    -0.07
    ennon
    -0.07
    noinspection
    -0.07
    toPromise
    -0.07
    vrier
    -0.06
    zial
    -0.06
    POSITIVE LOGITS
     Bust
    0.08
    busters
    0.07
    itution
    0.07
    ampo
    0.07
    .getvalue
    0.07
     Budd
    0.07
    agn
    0.07
    alion
    0.06
    af
    0.06
    OCK
    0.06
    Activations Density 0.003%

    No Known Activations