© 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. 129096
    Prev
    Next
    INDEX
    Explanations

    references to death and related circumstances

    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
    outu
    -0.07
     mastur
    -0.07
    arsi
    -0.07
    ìĿ´ìķ¼
    -0.07
    OKIE
    -0.07
    çĪ½
    -0.07
    erior
    -0.07
     kab
    -0.07
    ÑģÑĤоÑĢ
    -0.07
    ÑıÑĩи
    -0.07
    POSITIVE LOGITS
     reportedly
    0.08
     shock
    0.08
     heart
    0.07
     shocked
    0.06
     cause
    0.06
     studio
    0.06
     shocking
    0.06
    heart
    0.06
     death
    0.06
    tributes
    0.06
    Activations Density 0.011%

    No Known Activations