© 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. 9-LLAMASCOPE-RES-131K
    11. 95797
    Prev
    Next
    INDEX
    Explanations

    code related to initializing user interface components in a programming context

    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
     blink
    -0.07
    -validator
    -0.06
    /Dk
    -0.06
    æľ¬å½ĵ
    -0.06
    thern
    -0.06
    oÅĻ
    -0.06
    SPACE
    -0.06
    muz
    -0.06
    erb
    -0.06
    pekt
    -0.06
    POSITIVE LOGITS
    /Resources
    0.07
    åıĤ
    0.07
    avad
    0.07
    ombo
    0.06
     Americas
    0.06
    vard
    0.06
     нав
    0.06
    ÙĦاÙĦ
    0.06
    aspers
    0.06
    uffy
    0.06
    Activations Density 0.015%

    No Known Activations