© 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. 62958
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to species and their classifications

    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
     (~(
    -0.07
    ibri
    -0.07
    ksen
    -0.07
    addafi
    -0.07
    ourg
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    گاÙĩ
    -0.06
     DÃŃky
    -0.06
    ÑĢай
    -0.06
     //~
    -0.06
    POSITIVE LOGITS
     pall
    0.06
     metabolism
    0.06
    presso
    0.06
     Werner
    0.06
     åĽ
    0.06
    uraa
    0.06
     ins
    0.06
     пÑĢеÑģ
    0.06
    ÑĥлÑİ
    0.05
    Messaging
    0.05
    Activations Density 0.001%

    No Known Activations