© 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. 72356
    Prev
    Next
    INDEX
    Explanations

    elements of a conversation or interaction during phone calls

    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
    eldom
    -0.07
    pare
    -0.06
     Strict
    -0.06
    chyb
    -0.06
    Ã
    -0.06
     literal
    -0.06
     STRICT
    -0.06
     wakeup
    -0.06
    aphore
    -0.06
    repid
    -0.06
    POSITIVE LOGITS
     conversation
    0.07
    å¯Ĵ
    0.07
    atÃŃm
    0.06
    datable
    0.06
    Segue
    0.06
     tomorrow
    0.06
    atos
    0.06
     Conversation
    0.06
    Å¡ak
    0.06
    Ñģед
    0.06
    Activations Density 0.024%

    No Known Activations