© 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. 107911
    Prev
    Next
    INDEX
    Explanations

    references to communication and expression of emotions through body language

    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
    essor
    -0.07
    adh
    -0.06
     hy
    -0.06
    inta
    -0.06
    åIJ¹
    -0.06
     Phon
    -0.06
    785
    -0.06
     Voices
    -0.06
    udio
    -0.06
    erton
    -0.06
    POSITIVE LOGITS
     communication
    0.10
    communication
    0.10
     communicate
    0.10
    交æµģ
    0.09
     Communication
    0.09
     comunic
    0.08
     communicator
    0.08
     communicates
    0.08
    Communication
    0.08
     communicating
    0.08
    Activations Density 0.043%

    No Known Activations