© 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. 117063
    Prev
    Next
    INDEX
    Explanations

    emotional interactions 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
     Nag
    -0.06
    ould
    -0.06
    ă
    -0.06
    едÑĮ
    -0.06
     nag
    -0.06
    ë¶Ģ
    -0.06
    Äł
    -0.06
    Ñĸп
    -0.06
    uy
    -0.06
     sq
    -0.06
    POSITIVE LOGITS
     alf
    0.07
     Ñģвид
    0.07
    MOTE
    0.07
     âĢı
    0.07
    .descriptor
    0.06
    occo
    0.06
    richt
    0.06
     versus
    0.06
    kee
    0.06
    inel
    0.06
    Activations Density 0.020%

    No Known Activations