© 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. 17-LLAMASCOPE-RES-131K
    11. 30077
    Prev
    Next
    INDEX
    Explanations

    terms related to Pokémon abilities and strategies

    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
    ruba
    -0.07
    connexion
    -0.07
    eneg
    -0.07
    uchos
    -0.07
    ặt
    -0.07
     Fallon
    -0.07
     Hatch
    -0.06
     LGPL
    -0.06
    \Php
    -0.06
    hdl
    -0.06
    POSITIVE LOGITS
    orners
    0.06
     tournament
    0.06
    iry
    0.06
     decks
    0.06
     Strategies
    0.06
    éħįåIJĪ
    0.06
    ament
    0.06
    646
    0.06
    builder
    0.06
    Disallow
    0.06
    Activations Density 0.004%

    No Known Activations