© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69136
    Prev
    Next
    INDEX
    Explanations

    references to socio-political issues and cultural phenomena

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Įĵ
    -0.07
     :↵↵
    -0.06
    pekt
    -0.06
    :↵↵
    -0.06
    :↵↵↵
    -0.06
    UME
    -0.06
     ones
    -0.06
    ови
    -0.06
    cpy
    -0.06
    '),'
    -0.06
    POSITIVE LOGITS
    âĢ¬
    0.09
     å·Ŀ
    0.07
    ,www
    0.07
     ?,
    0.07
    ↵		↵
    0.07
    ↵	↵
    0.07
    	TokenName
    0.07
    atos
    0.07
    ?,
    0.07
    aimassage
    0.07
    Activations Density 0.028%

    No Known Activations