© 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. 71966
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and evaluations

    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
    ardon
    -0.08
    ummies
    -0.07
    onso
    -0.07
    utter
    -0.06
    gee
    -0.06
    erring
    -0.06
    defer
    -0.06
    DELAY
    -0.06
    å
    -0.06
    729
    -0.06
    POSITIVE LOGITS
     actually
    0.11
    actually
    0.09
     Actually
    0.08
    Actually
    0.08
     felt
    0.07
     actual
    0.07
    ç«Ł
    0.07
     Relief
    0.07
     relief
    0.06
    might
    0.06
    Activations Density 0.044%

    No Known Activations