© 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 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. 128784
    Prev
    Next
    INDEX
    Explanations

    terms related to social justice and economic disparity

    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
    ahoma
    -0.07
    uli
    -0.07
     imperson
    -0.06
    ceae
    -0.06
    enstein
    -0.06
    gte
    -0.06
    istrat
    -0.06
    961
    -0.06
    UCT
    -0.06
    uki
    -0.06
    POSITIVE LOGITS
     Hemp
    0.07
     ⣨
    0.07
     rdr
    0.06
     unavoid
    0.06
    opathy
    0.06
    é¢ij次
    0.06
     ãĢĪ
    0.06
     ICON
    0.06
    Legacy
    0.06
    jay
    0.06
    Activations Density 0.000%

    No Known Activations