© 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. 39740
    Prev
    Next
    INDEX
    Explanations

    mentions of legal outcomes and personal injuries in described events

    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
    uffman
    -0.06
     Walker
    -0.06
    utenberg
    -0.06
     walker
    -0.06
     Mort
    -0.06
     soup
    -0.06
     pedest
    -0.06
     onsite
    -0.06
     ØŃض
    -0.05
     Edison
    -0.05
    POSITIVE LOGITS
    Seat
    0.12
     passengers
    0.12
     seat
    0.12
     passenger
    0.11
     seats
    0.11
     interior
    0.11
    Interior
    0.11
    -seat
    0.11
     Seat
    0.10
    seat
    0.10
    Activations Density 0.142%

    No Known Activations