© 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. 18779
    Prev
    Next
    INDEX
    Explanations

    concepts related to graph theory and its properties

    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
    adera
    -0.08
    bj
    -0.08
    rl
    -0.07
     intox
    -0.06
    ieres
    -0.06
    awah
    -0.06
    iyat
    -0.06
    ovenant
    -0.06
    tc
    -0.06
    íĹĪ
    -0.06
    POSITIVE LOGITS
    onium
    0.07
     whose
    0.07
     Anc
    0.07
     Watts
    0.07
    ÙĤÛĮ
    0.06
    á»ĭch
    0.06
    adb
    0.06
    CallCheck
    0.06
    metic
    0.06
    isdigit
    0.06
    Activations Density 0.088%

    No Known Activations