© 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. 71134
    Prev
    Next
    INDEX
    Explanations

    references to airline emergencies and disruptions

    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
    elters
    -0.07
     Mattis
    -0.06
     curb
    -0.06
    ÑĥÑģÑĤа
    -0.06
    моÑĤ
    -0.06
    ovaly
    -0.06
     utilities
    -0.06
    lotte
    -0.06
    AGO
    -0.06
    issan
    -0.06
    POSITIVE LOGITS
     cabin
    0.10
     Cabin
    0.09
     passengers
    0.09
     onboard
    0.09
     cabins
    0.08
    IFE
    0.08
     steward
    0.08
     flight
    0.08
     passenger
    0.07
     crew
    0.07
    Activations Density 0.014%

    No Known Activations