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

    Neuronpedia

    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. 124853
    Prev
    Next
    INDEX
    Explanations

    discussions about growth and physical development in children

    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
     Alive
    -0.07
    renom
    -0.07
     unborn
    -0.07
    omik
    -0.07
    ylon
    -0.06
     наÑĢ
    -0.06
     ogs
    -0.06
    tron
    -0.06
    uchen
    -0.06
    acute
    -0.06
    POSITIVE LOGITS
     growth
    0.11
     Growth
    0.10
     Tanner
    0.09
     hormone
    0.09
    /pub
    0.09
     puberty
    0.09
     development
    0.08
     pub
    0.08
    growth
    0.08
     Development
    0.07
    Activations Density 0.010%

    No Known Activations