© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82758
    Prev
    Next
    INDEX
    Explanations

    customer service-related terms and phrases

    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
    imon
    -0.10
    ioni
    -0.07
    ÏĦια
    -0.07
    entine
    -0.07
    uien
    -0.06
    onth
    -0.06
     Interpret
    -0.06
    åĩºåĵģ
    -0.06
     lah
    -0.06
    lech
    -0.06
    POSITIVE LOGITS
     call
    0.07
     Call
    0.07
     CCTV
    0.06
    554
    0.06
     booking
    0.06
     Booking
    0.06
    acle
    0.06
     Pant
    0.06
    call
    0.06
    atin
    0.06
    Activations Density 0.022%

    No Known Activations