© 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 EvalsExportsinterp-engineNEWAPI 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. 31255
    Prev
    Next
    INDEX
    Explanations

    numerical data related to births

    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
    utenberg
    -0.07
    нед
    -0.06
     Sommer
    -0.06
    .son
    -0.06
    окон
    -0.06
    ibu
    -0.06
    ilogue
    -0.06
    logue
    -0.06
    strip
    -0.06
    esch
    -0.06
    POSITIVE LOGITS
     birth
    0.11
     born
    0.10
    çĶŁ
    0.10
     births
    0.10
     Birth
    0.10
    IRTH
    0.09
    _birth
    0.08
    -born
    0.08
    birth
    0.08
     Born
    0.07
    Activations Density 0.003%

    No Known Activations