© 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. 89701
    Prev
    Next
    INDEX
    Explanations

    elements related to recognition and public perception of specific individuals or events

    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
    oldem
    -0.08
    âce
    -0.07
    cef
    -0.07
    ää
    -0.07
    hoe
    -0.07
    blr
    -0.07
    iever
    -0.07
    utschen
    -0.07
    unu
    -0.07
    emade
    -0.07
    POSITIVE LOGITS
    æŁ±
    0.06
     sol
    0.06
    elo
    0.06
     Aug
    0.06
     fled
    0.05
    лÑıн
    0.05
    elder
    0.05
    nas
    0.05
     weights
    0.05
     coc
    0.05
    Activations Density 0.053%

    No Known Activations