© 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 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. 77303
    Prev
    Next
    INDEX
    Explanations

    HTML or web development-related terms

    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
    edes
    -0.07
    евой
    -0.07
     clo
    -0.07
    omik
    -0.07
    lint
    -0.07
    rtl
    -0.06
    .scalablytyped
    -0.06
    ÄĻd
    -0.06
    ney
    -0.06
    vala
    -0.06
    POSITIVE LOGITS
    ÅĻÃŃž
    0.07
    _FATAL
    0.07
    \Schema
    0.06
    eward
    0.06
    avr
    0.06
    _CERT
    0.06
    liers
    0.06
    ÑĢек
    0.06
    adr
    0.06
    ÅĻik
    0.06
    Activations Density 0.000%

    No Known Activations