© 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. 76587
    Prev
    Next
    INDEX
    Explanations

    elements related to hierarchical power dynamics and societal structures

    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
    znik
    -0.08
    onse
    -0.07
    kom
    -0.06
    åĢī
    -0.06
    ango
    -0.06
    çĨĬ
    -0.06
    ynamo
    -0.06
     Sugar
    -0.06
    icus
    -0.06
     Hulk
    -0.06
    POSITIVE LOGITS
     desert
    0.09
     Desert
    0.09
     Tucson
    0.07
     Mesa
    0.07
    Sanders
    0.07
    EATURE
    0.06
    ucson
    0.06
    çĸĨ
    0.06
    rxjs
    0.06
     Suns
    0.06
    Activations Density 0.001%

    No Known Activations