© 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. 17359
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and the importance of addressing systemic inequalities

    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
    Boot
    -0.06
    omez
    -0.06
    oub
    -0.06
    bor
    -0.06
    yu
    -0.06
    iph
    -0.06
    opping
    -0.06
     requestData
    -0.06
    okin
    -0.06
    obody
    -0.06
    POSITIVE LOGITS
    theme
    0.07
    strap
    0.07
     applied
    0.07
     theme
    0.07
     precisely
    0.07
    //{{
    0.07
    .Bunifu
    0.07
    Ø
    0.07
    OfClass
    0.07
    nage
    0.07
    Activations Density 0.070%

    No Known Activations