© 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. 59893
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous cultures and 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
    utta
    -0.08
    ajes
    -0.08
    agara
    -0.08
    serrat
    -0.08
    hma
    -0.08
    ipa
    -0.07
    pector
    -0.07
    áty
    -0.07
    tfoot
    -0.07
    taj
    -0.07
    POSITIVE LOGITS
     gene
    0.07
     tribal
    0.07
     Rabbit
    0.07
     Ireland
    0.07
     Gael
    0.07
     Dublin
    0.06
     Conor
    0.06
     Irish
    0.06
     Clan
    0.06
     spl
    0.06
    Activations Density 0.001%

    No Known Activations