© 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. 85928
    Prev
    Next
    INDEX
    Explanations

    references to ideologies and movements related to social justice and political theory

    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
    enko
    -0.08
    -io
    -0.07
    tesy
    -0.07
     Pioneer
    -0.07
    pee
    -0.07
    ·»
    -0.07
    reed
    -0.06
    zik
    -0.06
    esteem
    -0.06
    Transparent
    -0.06
    POSITIVE LOGITS
     princip
    0.06
     caret
    0.06
     rall
    0.06
     inheritance
    0.06
     Worker
    0.06
    ickets
    0.06
     betr
    0.06
    翼
    0.06
    æĶ¶å½ķ
    0.06
     rif
    0.06
    Activations Density 0.007%

    No Known Activations