© 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. 15201
    Prev
    Next
    INDEX
    Explanations

    phrases related to attendance and participation in events

    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
    âĢ¦
    -0.06
     almost
    -0.06
    -
    -0.06
    âĢ¦↵
    -0.06
    .
    -0.06
     last
    -0.06
     (
    -0.06
    aper
    -0.06
     logic
    -0.05
    POSITIVE LOGITS
     physical
    0.15
     physically
    0.15
    physical
    0.14
     Physical
    0.14
    Physical
    0.14
     fÃŃs
    0.13
     PHYS
    0.13
     physic
    0.12
     ÑĦÑĸз
    0.12
    çī©çIJĨ
    0.11
    Activations Density 0.010%

    No Known Activations