© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    terms related to programming constructs and error handling

    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
    мелÑĮ
    -0.07
    @js
    -0.06
    606
    -0.06
    ź
    -0.06
     pis
    -0.06
    (æĹ¥
    -0.06
    elper
    -0.06
    edn
    -0.06
    ustin
    -0.06
     Retro
    -0.06
    POSITIVE LOGITS
    mary
    0.07
    aupt
    0.06
    t
    0.06
     nhau
    0.06
     Ded
    0.06
    ania
    0.06
    207
    0.06
    iece
    0.06
    ovice
    0.06
    nerg
    0.06
    Activations Density 0.013%

    No Known Activations