© 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. 85843
    Prev
    Next
    INDEX
    Explanations

    JavaScript and HTML-related function calls and elements

    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
    ìĦľëĬĶ
    -0.07
     gele
    -0.07
    pte
    -0.07
    adelphia
    -0.07
    ÑĢик
    -0.07
    zi
    -0.07
    avin
    -0.07
    achu
    -0.07
    acha
    -0.07
    (Yii
    -0.07
    POSITIVE LOGITS
    onis
    0.08
     Gross
    0.07
    on
    0.07
     Alice
    0.06
    s
    0.06
     AIM
    0.06
    t
    0.06
    Alice
    0.05
    ment
    0.05
    onet
    0.05
    Activations Density 0.001%

    No Known Activations