© 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. 42824
    Prev
    Next
    INDEX
    Explanations

    palabras relacionadas con la fotografía, la identidad cultural y el activismo social

    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
    hana
    -0.08
    èĵ
    -0.07
    abei
    -0.07
    actable
    -0.07
    aly
    -0.07
    ा:
    -0.07
    emy
    -0.07
    гл
    -0.07
    rimon
    -0.06
    ợi
    -0.06
    POSITIVE LOGITS
     Edition
    0.09
     edition
    0.07
    860
    0.06
    ót
    0.06
    pton
    0.06
    angan
    0.06
    uxe
    0.06
    ument
    0.05
     &
    0.05
    &q
    0.05
    Activations Density 0.060%

    No Known Activations