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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39953
    Prev
    Next
    INDEX
    Explanations

    emotional discussions about interpersonal relationships

    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
    urette
    -0.08
    zas
    -0.07
    Ãło
    -0.07
    ovÃŃ
    -0.07
    adiens
    -0.07
    onen
    -0.07
    ismet
    -0.07
    ÄĽstÃŃ
    -0.07
    ugi
    -0.07
    ellas
    -0.07
    POSITIVE LOGITS
     toxic
    0.07
     toxicity
    0.06
     hurt
    0.06
    BX
    0.06
     minim
    0.06
     estr
    0.06
     communication
    0.06
     contact
    0.06
    tone
    0.05
     Corm
    0.05
    Activations Density 0.005%

    No Known Activations