© 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 EvalsExportsinterp-engineNEWAPI 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. 93059
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and survivor mentions in obituaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names of people, places, dates, times, prices, specific personal identifiers, and distinctive objects that would typically be found in database records, listings, announcements, legal documents, or biographical information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     famously
    -0.06
    -0.06
    ,and
    -0.06
     μÏĢοÏģοÏį
    -0.05
    -0.05
    amp
    -0.05
     classics
    -0.05
    Ìģt
    -0.05
    ,but
    -0.05
    id
    -0.05
    POSITIVE LOGITS
    @nate
    0.09
    .getSeconds
    0.09
    iyel
    0.08
     EXEMPLARY
    0.08
    fragistics
    0.08
    eyse
    0.08
    OptionsResolver
    0.08
    GenerationStrategy
    0.08
    	throws
    0.08
    /**č↵
    0.08
    Activations Density 13.021%

    No Known Activations