© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    discussions about job options, evaluations of wealth, and queries related to assistance or protection in various contexts

    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
    ellan
    -0.08
    ynes
    -0.07
    etto
    -0.07
    banana
    -0.07
    bette
    -0.07
    EDITOR
    -0.07
    é¦Ļèķī
    -0.06
    ouston
    -0.06
    zim
    -0.06
    eph
    -0.06
    POSITIVE LOGITS
    /stretch
    0.07
    gas
    0.07
    _FT
    0.06
    ruz
    0.06
    .defaults
    0.06
    ags
    0.06
    imbus
    0.06
    еÑĢÑĤи
    0.06
    nce
    0.06
    _TC
    0.06
    Activations Density 0.008%

    No Known Activations