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

    Neuronpedia

    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. 120023
    Prev
    Next
    INDEX
    Explanations

    instances of demographic references and group identities

    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
    ierge
    -0.07
    intl
    -0.07
    asl
    -0.07
    anche
    -0.07
    اءات
    -0.07
    csr
    -0.06
    Via
    -0.06
    @update
    -0.06
    illis
    -0.06
     ÙĪÙĦÙĬ
    -0.06
    POSITIVE LOGITS
     among
    0.11
     amongst
    0.10
    among
    0.08
     Among
    0.08
    utex
    0.08
     present
    0.07
    pard
    0.06
    Among
    0.06
     ÑģÑĢеди
    0.06
     exist
    0.06
    Activations Density 0.037%

    No Known Activations