© 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. 9-LLAMASCOPE-RES-131K
    11. 97242
    Prev
    Next
    INDEX
    Explanations

    references to political commentary and social issues

    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
    enden
    -0.08
    rix
    -0.06
     Troy
    -0.06
    ooo
    -0.06
    ajs
    -0.06
    çĴ
    -0.06
    oon
    -0.06
    ÏĨÏħ
    -0.05
    slash
    -0.05
     Gender
    -0.05
    POSITIVE LOGITS
    edBy
    0.08
    /tutorial
    0.06
     示
    0.06
     ary
    0.06
    arning
    0.06
    udad
    0.06
    amework
    0.06
    ắn
    0.06
    bach
    0.06
     Demon
    0.06
    Activations Density 0.065%

    No Known Activations