© 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. 27513
    Prev
    Next
    INDEX
    Explanations

    code syntax and variable assignments in programming contexts

    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
    agon
    -0.08
    zos
    -0.08
    .ManyToMany
    -0.08
    eras
    -0.07
    .MixedReality
    -0.07
    anou
    -0.07
    ÚĺÙĩ
    -0.07
    enberg
    -0.07
    Ÿ
    -0.07
    .addObject
    -0.07
    POSITIVE LOGITS
     require
    0.09
    require
    0.07
    (require
    0.06
    cls
    0.06
    =require
    0.06
     shard
    0.06
     requiring
    0.06
    	require
    0.06
     requires
    0.06
    .require
    0.05
    Activations Density 0.004%

    No Known Activations