© 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. 17456
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous cultural resources and educational content

    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
    addy
    -0.06
    .Formatting
    -0.06
     finish
    -0.06
     DISTRIBUT
    -0.06
    ier
    -0.06
    .poster
    -0.06
    .checkBox
    -0.06
    ollo
    -0.06
     Colomb
    -0.06
     bin
    -0.06
    POSITIVE LOGITS
     resource
    0.08
     Useful
    0.08
     useful
    0.07
    /resources
    0.07
    (Resource
    0.07
    (resource
    0.07
    -resource
    0.07
    .resource
    0.07
     ResourceType
    0.07
    awe
    0.07
    Activations Density 0.016%

    No Known Activations