© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3584
    Prev
    Next
    INDEX
    Explanations

    information regarding casualties and fatalities in news reports

    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
    arsi
    -0.06
    resh
    -0.06
    anches
    -0.06
    à¸Ľ
    -0.06
    ault
    -0.06
     hi
    -0.06
    á»Ļn
    -0.05
    icious
    -0.05
     Illustrated
    -0.05
    763
    -0.05
    POSITIVE LOGITS
     died
    0.08
     RIP
    0.08
     yesterday
    0.07
    strup
    0.07
    Yesterday
    0.07
    å§ĵåIJį
    0.07
    æĺ¨
    0.07
     deaths
    0.07
     fatalities
    0.07
     identities
    0.07
    Activations Density 0.014%

    No Known Activations