© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88939
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to changes, observations, and effects in the context of legislation and community dynamics

    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
    istrovstvÃŃ
    -0.09
    enberg
    -0.06
    olumn
    -0.06
    SError
    -0.06
    amoto
    -0.06
    dni
    -0.06
    rell
    -0.06
    _VERTEX
    -0.06
     Lanka
    -0.06
    STYPE
    -0.06
    POSITIVE LOGITS
     ë°Ķë¡ľ
    0.07
     {}:
    0.06
    è¯Ŀ
    0.06
    _boot
    0.06
    à¥Ĥà¤Ľ
    0.06
    ünd
    0.06
    roupe
    0.06
     titled
    0.06
    боÑĢ
    0.06
     наз
    0.06
    Activations Density 0.031%

    No Known Activations