© 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. 2481
    Prev
    Next
    INDEX
    Explanations

    elements related to action and emotional 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
    éŀ
    -0.08
    ãĥ¡ãĥ©
    -0.07
     ourselves
    -0.07
    nel
    -0.07
    ecut
    -0.07
    izzo
    -0.06
    æĺ¯æĪij
    -0.06
    é£İéĻ©
    -0.06
    еÑĢин
    -0.06
    afari
    -0.06
    POSITIVE LOGITS
    uder
    0.06
     Jarvis
    0.06
    ÄįÃŃ
    0.06
     fict
    0.06
     conventional
    0.06
     fictional
    0.05
     Herr
    0.05
    اÙ
    0.05
     Schmidt
    0.05
     presumably
    0.05
    Activations Density 0.003%

    No Known Activations