© 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. 17-LLAMASCOPE-RES-131K
    11. 116785
    Prev
    Next
    INDEX
    Explanations

    various types of closing syntax and delimiters in code

    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
    mojom
    -0.09
    ieres
    -0.07
    GetSize
    -0.07
    enga
    -0.07
    angelog
    -0.07
    nothrow
    -0.07
    aeda
    -0.07
    SupportActionBar
    -0.07
    RefreshLayout
    -0.07
     strSql
    -0.07
    POSITIVE LOGITS
    ium
    0.06
    sei
    0.06
     break
    0.06
     pass
    0.05
     Sur
    0.05
    ht
    0.05
    anna
    0.05
     assert
    0.05
     **
    0.05
     [
    0.05
    Activations Density 0.038%

    No Known Activations