© 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. 17298
    Prev
    Next
    INDEX
    Explanations

    titles and names related to video games and their qualities

    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
    fish
    -0.07
    IQ
    -0.06
     Dale
    -0.06
     Jurassic
    -0.06
    ãĥĨãĥ«
    -0.06
    ee
    -0.06
    eki
    -0.06
    ìĥī
    -0.06
    æľĹ
    -0.06
     Bee
    -0.06
    POSITIVE LOGITS
    ogne
    0.07
    emie
    0.07
    бав
    0.07
    اÙĪÙĬØ©
    0.07
    gnore
    0.07
     Circular
    0.07
    ÏĦοÏħ
    0.07
     Leone
    0.07
     verg
    0.07
     Leban
    0.06
    Activations Density 0.001%

    No Known Activations