© 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. 73789
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure in programming

    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
    944
    -0.08
    riangle
    -0.07
    -caret
    -0.07
    alty
    -0.07
    iani
    -0.07
     dikke
    -0.07
    .netflix
    -0.07
    .appspot
    -0.07
    zel
    -0.07
    asad
    -0.07
    POSITIVE LOGITS
     b
    0.07
     Minor
    0.06
     Rin
    0.06
     bob
    0.06
    çºĮ
    0.05
    Minor
    0.05
    AMED
    0.05
    лл
    0.05
     av
    0.05
    .owl
    0.05
    Activations Density 0.628%

    No Known Activations