© 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. 3095
    Prev
    Next
    INDEX
    Explanations

    structured programming elements, particularly those related to function parameters and types

    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
    ÌĨ
    -0.07
    omanip
    -0.07
    _NT
    -0.07
     LOD
    -0.06
    _bindings
    -0.06
     scar
    -0.06
    ãĢħ
    -0.06
     Gratis
    -0.06
    รร
    -0.06
    .job
    -0.06
    POSITIVE LOGITS
    et
    0.07
    ets
    0.07
    eth
    0.07
    )
    0.06
     lô
    0.06
     aras
    0.06
     GlobalKey
    0.06
    èª
    0.06
    undefined
    0.06
    .getCurrentUser
    0.06
    Activations Density 0.028%

    No Known Activations