© 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. 17445
    Prev
    Next
    INDEX
    Explanations

    instances of communication and interaction between characters

    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
     Bra
    -0.07
    adera
    -0.07
     bra
    -0.07
     목ìĨĮ
    -0.07
     Streets
    -0.07
    åĿ¦
    -0.07
    uevo
    -0.07
    ->__
    -0.06
     voices
    -0.06
     bre
    -0.06
    POSITIVE LOGITS
     communicated
    0.09
     communicate
    0.09
     communication
    0.08
     Communication
    0.08
     Communic
    0.07
    communication
    0.07
     communicates
    0.07
     коммÑĥ
    0.07
     comunic
    0.07
    Communication
    0.07
    Activations Density 0.016%

    No Known Activations