© 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. 17-LLAMASCOPE-RES-131K
    11. 71893
    Prev
    Next
    INDEX
    Explanations

    comment indicators and debug statements 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
     blah
    -0.06
    concat
    -0.06
    avi
    -0.06
    Ïħ
    -0.06
    /on
    -0.05
    oggle
    -0.05
     HttpServletResponse
    -0.05
    jan
    -0.05
     TAS
    -0.05
     Mort
    -0.05
    POSITIVE LOGITS
    deme
    0.07
    raci
    0.07
     çIJ
    0.07
    íĥĦ
    0.07
     rencont
    0.07
    ÐĶÐIJ
    0.07
     setBackgroundImage
    0.07
    aket
    0.07
    ê·¹
    0.06
     escorte
    0.06
    Activations Density 0.009%

    No Known Activations