© 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. 92185
    Prev
    Next
    INDEX
    Explanations

    references to communities or regions, particularly in relation to services and features available to them

    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
    oui
    -0.06
    วย
    -0.05
    aptic
    -0.05
    .toObject
    -0.05
    anel
    -0.05
    é½IJ
    -0.05
     Mapper
    -0.05
    ).__
    -0.05
    ently
    -0.05
    pod
    -0.05
    POSITIVE LOGITS
     surrounding
    0.13
     vicinity
    0.12
     beyond
    0.11
     surrounds
    0.11
     Surround
    0.11
     surroundings
    0.10
     env
    0.10
     elsewhere
    0.10
    Beyond
    0.09
    eyond
    0.09
    Activations Density 0.031%

    No Known Activations