© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    Java programming syntax and structure

    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
    cir
    -0.06
     Ker
    -0.06
     Mitch
    -0.06
    otech
    -0.06
    alias
    -0.05
     disposition
    -0.05
     ry
    -0.05
    iod
    -0.05
     ware
    -0.05
    ioc
    -0.05
    POSITIVE LOGITS
    821
    0.07
    BuilderInterface
    0.07
    initializer
    0.07
    uitka
    0.07
    $LANG
    0.06
    Ấ
    0.06
    521
    0.06
    _finalize
    0.06
    ena
    0.06
    ABA
    0.06
    Activations Density 0.001%

    No Known Activations