© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84410
    Prev
    Next
    INDEX
    Explanations

    expressions of mental states and emotional conditions

    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
    arda
    -0.07
    åIJ¸
    -0.07
    statt
    -0.07
    antino
    -0.07
    /boot
    -0.06
     Kir
    -0.06
    ssc
    -0.06
    oser
    -0.06
    oms
    -0.06
    acha
    -0.06
    POSITIVE LOGITS
     intact
    0.07
     levels
    0.07
     Courier
    0.06
     highest
    0.06
     Alley
    0.06
     bar
    0.06
     Inv
    0.06
     meter
    0.06
    .hxx
    0.06
     lever
    0.06
    Activations Density 0.037%

    No Known Activations