© 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. 62777
    Prev
    Next
    INDEX
    Explanations

    significant events and contributions related to social justice movements

    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
    emez
    -0.07
    ylko
    -0.07
     global
    -0.07
    193
    -0.07
    195
    -0.06
     WWII
    -0.06
    .scalablytyped
    -0.06
    inez
    -0.06
    rar
    -0.06
    global
    -0.06
    POSITIVE LOGITS
    186
    0.14
     Confederate
    0.11
     Union
    0.10
    187
    0.09
     Reconstruction
    0.09
    185
    0.09
    Union
    0.09
    184
    0.09
     Civil
    0.09
     CSA
    0.08
    Activations Density 0.051%

    No Known Activations