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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125954
    Prev
    Next
    INDEX
    Explanations

    references to violent or aggressive actions related to individuals

    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
     drive
    -0.08
     drives
    -0.07
     Alley
    -0.07
    -drive
    -0.07
     roads
    -0.07
     Drive
    -0.07
    ewire
    -0.07
    drive
    -0.07
     Gil
    -0.06
     driv
    -0.06
    POSITIVE LOGITS
     passengers
    0.10
     onboard
    0.09
     seat
    0.09
     passenger
    0.08
     seats
    0.08
     Seats
    0.08
     Passenger
    0.07
    -seat
    0.07
     Seat
    0.07
     fares
    0.07
    Activations Density 0.027%

    No Known Activations