© 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. 15-LLAMASCOPE-RES-131K
    11. 89266
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional engagement and reactions to media

    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
    intval
    -0.07
    @update
    -0.07
     update
    -0.07
    _CLI
    -0.06
    itten
    -0.06
    _RTC
    -0.06
    hoe
    -0.06
    pedo
    -0.06
    asts
    -0.06
    нож
    -0.06
    POSITIVE LOGITS
    Finish
    0.07
    peria
    0.07
    recommended
    0.07
    kea
    0.06
    finish
    0.06
    elden
    0.06
    jeta
    0.06
    _SUFFIX
    0.06
    unday
    0.06
     finish
    0.06
    Activations Density 0.021%

    No Known Activations