© 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. 108710
    Prev
    Next
    INDEX
    Explanations

    the word "that" 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
    ãģĤãĤĭ
    -0.08
    Ùĩ
    -0.08
    ised
    -0.07
    ãģĤãĤĬ
    -0.07
     Halk
    -0.07
     Bol
    -0.06
    ãģĤãģ£ãģŁ
    -0.06
    adin
    -0.06
    s
    -0.06
    us
    -0.06
    POSITIVE LOGITS
    ched
    0.14
    /th
    0.12
    ching
    0.11
     particular
    0.10
    zelf
    0.10
    -ÑĤо
    0.09
    chy
    0.09
     same
    0.09
    gene
    0.09
    curity
    0.09
    Activations Density 0.138%

    No Known Activations