© 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. 93852
    Prev
    Next
    INDEX
    Explanations

    references to local governance or local communities

    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
    JR
    -0.07
    гÑĢа
    -0.07
    ÑģÑı
    -0.07
    ogh
    -0.07
    idel
    -0.07
    âĺħ
    -0.07
    å¹ķ
    -0.07
    /light
    -0.07
    drawing
    -0.07
    eson
    -0.06
    POSITIVE LOGITS
    ised
    0.15
    /local
    0.15
    vore
    0.14
    /global
    0.12
    ities
    0.12
    -global
    0.12
    -local
    0.11
    /reg
    0.11
    isation
    0.11
    izing
    0.11
    Activations Density 0.035%

    No Known Activations