© 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. 96204
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "public" in various contexts

    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
    alla
    -0.08
    ERGE
    -0.07
    deaux
    -0.07
     Grat
    -0.07
    aland
    -0.07
    enne
    -0.07
     abras
    -0.07
    lla
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ÏĨÏħ
    -0.07
    POSITIVE LOGITS
    afil
    0.06
     vari
    0.06
    cepts
    0.06
     substitution
    0.06
    ikt
    0.06
     Ray
    0.06
     dire
    0.05
     variability
    0.05
    chsel
    0.05
    vari
    0.05
    Activations Density 0.000%

    No Known Activations