© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75060
    Prev
    Next
    INDEX
    Explanations

    references to Mother's Day celebrations and related themes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    uyá»ģn
    -0.06
    andal
    -0.06
    ë§ī
    -0.06
     dziew
    -0.06
    ViewState
    -0.06
     Halloween
    -0.06
     consenting
    -0.06
    unal
    -0.06
    umed
    -0.06
     Greenwood
    -0.06
    POSITIVE LOGITS
     Father
    0.08
     father
    0.07
    ä¸Ī
    0.07
     Mother
    0.07
     fathers
    0.07
    íĭ
    0.07
     sentiment
    0.07
    Mother
    0.07
    /rem
    0.07
    Father
    0.07
    Activations Density 0.015%

    No Known Activations