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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73514
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reactions in narrative contexts

    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
    ãģ¡ãģ¯
    -0.08
    borg
    -0.07
    âĸ²
    -0.06
    uled
    -0.06
    errat
    -0.06
    OAD
    -0.06
    uml
    -0.06
    umbn
    -0.06
    足
    -0.06
    anza
    -0.06
    POSITIVE LOGITS
     indifference
    0.10
     normal
    0.10
     calmly
    0.09
     matter
    0.08
     NORMAL
    0.08
     simply
    0.07
     shrugged
    0.07
     perfectly
    0.07
     casually
    0.07
     shr
    0.07
    Activations Density 0.074%

    No Known Activations