© 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. 15-LLAMASCOPE-RES-131K
    11. 86826
    Prev
    Next
    INDEX
    Explanations

    formatting or syntax components in code

    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
    ynos
    -0.07
    adoo
    -0.06
     خارجÙĬØ©
    -0.06
     Memor
    -0.06
     tease
    -0.06
     setFrame
    -0.06
    MainFrame
    -0.06
    ichel
    -0.06
    okol
    -0.06
    ophile
    -0.06
    POSITIVE LOGITS
    .newBuilder
    0.07
    SharedPointer
    0.07
    णन
    0.06
    Å¡ak
    0.06
    onian
    0.06
    tutorial
    0.06
    ondo
    0.06
     èį
    0.06
    SSION
    0.06
    -sama
    0.06
    Activations Density 0.000%

    No Known Activations