© 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. 9-LLAMASCOPE-RES-131K
    11. 94554
    Prev
    Next
    INDEX
    Explanations

    terms related to political and governmental structures, particularly those associated with communism

    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
     æĿ¡
    -0.07
     Hust
    -0.06
    aint
    -0.06
    дина
    -0.06
    æĿ¡
    -0.06
    275
    -0.06
     chap
    -0.06
    tor
    -0.06
     Lore
    -0.06
    toi
    -0.06
    POSITIVE LOGITS
    gon
    0.08
    ewood
    0.07
    )":
    0.07
    jev
    0.07
    strup
    0.07
    agi
    0.06
    ÛĮزÛĮ
    0.06
    abbo
    0.06
    neh
    0.06
    첨ë¶Ģ
    0.06
    Activations Density 0.025%

    No Known Activations