© 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. 72992
    Prev
    Next
    INDEX
    Explanations

    references to group dynamics and collective experiences

    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
    axter
    -0.06
     TV
    -0.06
     modern
    -0.06
    hack
    -0.06
    onga
    -0.05
     earned
    -0.05
    unde
    -0.05
     AC
    -0.05
    éĥ¨
    -0.05
     Tage
    -0.05
    POSITIVE LOGITS
    ptron
    0.08
     LIABILITY
    0.08
     membership
    0.07
    membership
    0.07
    ÑĸÑĩ
    0.07
    uchs
    0.07
    ä¸ĢåĮº
    0.07
    apes
    0.07
    ismet
    0.07
    members
    0.07
    Activations Density 0.002%

    No Known Activations