© 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. 70899
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving violence or casualties

    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
    CI
    -0.07
    cia
    -0.07
    reeNode
    -0.07
    .ci
    -0.07
     CIA
    -0.07
    pair
    -0.06
    SizeMode
    -0.06
     DevComponents
    -0.06
    кÑĥÑģ
    -0.06
    mys
    -0.06
    POSITIVE LOGITS
     reports
    0.09
     local
    0.08
     report
    0.08
     ?>"/>↵
    0.07
     reporting
    0.07
     sources
    0.07
     reported
    0.07
    reports
    0.07
     unofficial
    0.07
     eyewitness
    0.07
    Activations Density 0.034%

    No Known Activations