© 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. 104082
    Prev
    Next
    INDEX
    Explanations

    variations of the word "balloon."

    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
    ea
    -0.08
    ford
    -0.08
    ROTO
    -0.07
    zelf
    -0.07
    lis
    -0.07
    eor
    -0.07
    lemen
    -0.07
    ONGL
    -0.07
    AKE
    -0.07
    eler
    -0.07
    POSITIVE LOGITS
    ctl
    0.07
    -headed
    0.07
    /window
    0.07
    -shaped
    0.06
     Gig
    0.06
    Å¡ka
    0.06
    /document
    0.06
    æĺł
    0.06
    arium
    0.06
    gebra
    0.06
    Activations Density 0.004%

    No Known Activations