© 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. 120656
    Prev
    Next
    INDEX
    Explanations

    mentions of the Republican Party and related terms

    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
    reib
    -0.07
    owel
    -0.06
    aday
    -0.06
    ruž
    -0.06
    лиÑĨ
    -0.06
    gers
    -0.06
    оÑĤÑĮ
    -0.06
    /body
    -0.06
    ÌĢ
    -0.06
    ovice
    -0.06
    POSITIVE LOGITS
     Party
    0.08
    -leaning
    0.08
    _PTR
    0.08
    rieve
    0.07
    ities
    0.07
    ische
    0.07
    ischer
    0.07
    htm
    0.07
    anism
    0.07
    -controlled
    0.07
    Activations Density 0.009%

    No Known Activations