© 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. 116421
    Prev
    Next
    INDEX
    Explanations

    variations of the word "av."

    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
    edes
    -0.08
    raph
    -0.07
    attery
    -0.07
    empo
    -0.07
    .intellij
    -0.07
     Pax
    -0.07
    iday
    -0.07
    ingt
    -0.06
     Bair
    -0.06
    mpl
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĩãĤ£
    0.07
    ero
    0.06
    bow
    0.06
    uds
    0.06
     Brock
    0.06
    tern
    0.06
     Moo
    0.06
    ÙĪرÙĩ
    0.06
    vana
    0.06
     micro
    0.05
    Activations Density 0.022%

    No Known Activations