© 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. 74738
    Prev
    Next
    INDEX
    Explanations

    actions related to rescue and assistance during emergencies or crises

    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
    Ymd
    -0.07
    chers
    -0.07
    erno
    -0.07
    edere
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    лекÑģанд
    -0.07
    .Selenium
    -0.07
    Disappear
    -0.07
     $("#"
    -0.07
    ·
    -0.07
    POSITIVE LOGITS
     stranded
    0.08
     trapped
    0.08
     ect
    0.07
     hostages
    0.06
     bob
    0.06
    mony
    0.06
     unconscious
    0.06
     from
    0.06
     khá»ıi
    0.06
     endangered
    0.05
    Activations Density 0.016%

    No Known Activations