© 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. 121653
    Prev
    Next
    INDEX
    Explanations

    references to Mother's Day and its historical significance

    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
    hausen
    -0.07
    leans
    -0.07
    eya
    -0.07
    _FMT
    -0.07
    abox
    -0.07
    ivel
    -0.06
    OPS
    -0.06
     Relatives
    -0.06
    fav
    -0.06
    amedi
    -0.06
    POSITIVE LOGITS
     cit
    0.07
     alike
    0.07
    blood
    0.06
     bonus
    0.06
    岡
    0.06
    èªł
    0.06
    /native
    0.06
    ANE
    0.06
     Nie
    0.06
    anta
    0.06
    Activations Density 0.004%

    No Known Activations