© 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. 129380
    Prev
    Next
    INDEX
    Explanations

    instances of debate or discussion in a political context

    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
    istrovstvÃŃ
    -0.08
     rencont
    -0.08
     proh
    -0.08
     kå
    -0.08
    -tm
    -0.07
    ÏĨÏĮ
    -0.07
    -scrollbar
    -0.07
    ViewById
    -0.07
    entai
    -0.07
    ARRIER
    -0.07
    POSITIVE LOGITS
     reference
    0.07
     audience
    0.07
     attack
    0.06
    SOLE
    0.06
     interrupt
    0.06
     attacks
    0.06
     refer
    0.06
     seconds
    0.06
     response
    0.06
     claims
    0.06
    Activations Density 0.007%

    No Known Activations