© 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. 70814
    Prev
    Next
    INDEX
    Explanations

    references to influential or notable individuals and their societal roles

    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
    #ad
    -0.07
    _ISR
    -0.07
    enco
    -0.07
    otas
    -0.07
    ucu
    -0.07
    ’te
    -0.07
    mal
    -0.07
    aris
    -0.07
    _ED
    -0.07
    ôt
    -0.07
    POSITIVE LOGITS
     who
    0.08
     (
    0.07
     whom
    0.07
     or
    0.07
    747
    0.07
    who
    0.06
     types
    0.06
    unker
    0.06
     completely
    0.06
     honorary
    0.05
    Activations Density 0.048%

    No Known Activations