© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15631
    Prev
    Next
    INDEX
    Explanations

    references to marginalized or fringe political ideas and groups

    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
    eel
    -0.07
    jÃŃž
    -0.07
    rie
    -0.07
     Amph
    -0.07
    lek
    -0.07
    овÑĥ
    -0.06
    eck
    -0.06
    oir
    -0.06
    smith
    -0.06
    ovich
    -0.06
    POSITIVE LOGITS
    /ext
    0.08
    /back
    0.07
    /end
    0.07
     marg
    0.07
    /out
    0.07
    /on
    0.07
     margins
    0.07
     marginal
    0.06
    357
    0.06
    -left
    0.06
    Activations Density 0.010%

    No Known Activations