© 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. 127049
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or help

    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
    illet
    -0.06
     Doch
    -0.06
    ики
    -0.06
    art
    -0.06
    ildo
    -0.06
     GetString
    -0.06
    als
    -0.06
    æŁĦ
    -0.06
     Self
    -0.06
    pron
    -0.06
    POSITIVE LOGITS
    --------------------------------------------------------------------------↵
    0.07
    _inventory
    0.07
    jni
    0.07
    zilla
    0.07
    GGLE
    0.07
    ä¸Ģä¸ĭ
    0.07
    VENTORY
    0.06
    ivÄĽ
    0.06
    adel
    0.06
    .getOwnProperty
    0.06
    Activations Density 0.003%

    No Known Activations