© 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. 106239
    Prev
    Next
    INDEX
    Explanations

    the name "Sue" and its variations or references in context

    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
    retty
    -0.07
    maal
    -0.06
    ne
    -0.06
    aurus
    -0.06
    AMY
    -0.06
     Parties
    -0.06
    cona
    -0.06
    иÑĩно
    -0.06
    nen
    -0.06
    ity
    -0.06
    POSITIVE LOGITS
    lessly
    0.08
    porno
    0.08
    esp
    0.07
    ños
    0.07
    bert
    0.07
    iras
    0.07
    bidden
    0.07
    ares
    0.07
    zilla
    0.07
    cloth
    0.07
    Activations Density 0.002%

    No Known Activations