© 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. 89399
    Prev
    Next
    INDEX
    Explanations

    references to indigenous tribes and cultural 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
    ersh
    -0.08
    omo
    -0.08
    elyn
    -0.07
    curity
    -0.07
    stor
    -0.07
    sak
    -0.07
     italia
    -0.06
    umen
    -0.06
    issance
    -0.06
    lio
    -0.06
    POSITIVE LOGITS
    -speaking
    0.10
    -Russian
    0.08
    -spe
    0.08
     Nadu
    0.07
    orum
    0.07
    ischer
    0.07
    -American
    0.07
     Convention
    0.07
     Controlled
    0.06
    -dominated
    0.06
    Activations Density 0.030%

    No Known Activations