© 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. 80696
    Prev
    Next
    INDEX
    Explanations

    the word "Trinity" and its variations 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
    NESS
    -0.08
    pron
    -0.08
    queries
    -0.08
    à¸Ńà¸ļ
    -0.08
    issement
    -0.07
    shal
    -0.07
    ibus
    -0.07
    аÑĤо
    -0.07
    orre
    -0.07
    roulette
    -0.07
    POSITIVE LOGITS
     Nielsen
    0.06
    ãģ¡ãĤĥ
    0.06
     ref
    0.06
    座
    0.06
    anning
    0.06
    ataka
    0.06
    -blue
    0.06
     Kelley
    0.06
     bypass
    0.05
    mite
    0.05
    Activations Density 0.003%

    No Known Activations