© 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. 71230
    Prev
    Next
    INDEX
    Explanations

    references to software features and permissions

    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
    ẻ
    -0.08
    adÃŃ
    -0.07
    /orders
    -0.07
    ãİ
    -0.07
     wann
    -0.07
    uml
    -0.07
    çijŁ
    -0.07
    _inches
    -0.07
    /packages
    -0.07
    istra
    -0.06
    POSITIVE LOGITS
    gtest
    0.07
     ÑĥÑģл
    0.06
     whitelist
    0.06
    uzu
    0.06
    otted
    0.06
     entirety
    0.06
     DCHECK
    0.06
    endoza
    0.06
    endale
    0.06
     desc
    0.05
    Activations Density 0.001%

    No Known Activations