© 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. 78666
    Prev
    Next
    INDEX
    Explanations

    references to racial disparities and statistics regarding incarceration rates

    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
    slu
    -0.08
    .)↵↵↵↵
    -0.07
    illac
    -0.07
    .cf
    -0.07
    ffe
    -0.07
    steder
    -0.07
    erno
    -0.07
    ieu
    -0.07
    rove
    -0.06
    Resistance
    -0.06
    POSITIVE LOGITS
     representation
    0.08
     Representation
    0.07
    representation
    0.07
    449
    0.06
    551
    0.06
    acs
    0.06
     representations
    0.06
    549
    0.06
     disproportion
    0.06
    991
    0.06
    Activations Density 0.011%

    No Known Activations