© 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. 9-LLAMASCOPE-RES-131K
    11. 98789
    Prev
    Next
    INDEX
    Explanations

    code structures and declarations that involve mapping or defining arrays and lists

    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
    ataka
    -0.07
    okit
    -0.07
    antar
    -0.06
     aValue
    -0.06
    onth
    -0.06
    ollo
    -0.06
     vá
    -0.06
     TestCase
    -0.06
    aku
    -0.06
    й
    -0.06
    POSITIVE LOGITS
    klad
    0.06
    -CN
    0.06
    trace
    0.06
    &action
    0.06
    tera
    0.06
    _CN
    0.06
    еви
    0.06
    ->__
    0.06
     tez
    0.06
    ãģĨãĤĵ
    0.06
    Activations Density 0.075%

    No Known Activations