© 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. 9-LLAMASCOPE-RES-131K
    11. 97541
    Prev
    Next
    INDEX
    Explanations

    programming-related error messages and user interface attributes

    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
    ÃŃlia
    -0.07
    ibar
    -0.07
    enen
    -0.07
     Bened
    -0.07
    iya
    -0.06
    905
    -0.06
     Rosenstein
    -0.06
    NSE
    -0.06
    nen
    -0.06
    nan
    -0.06
    POSITIVE LOGITS
    etter
    0.07
    ilt
    0.07
    veis
    0.06
    errer
    0.06
    isher
    0.06
    idden
    0.06
     Isl
    0.06
    gesi
    0.06
    анов
    0.06
    icago
    0.06
    Activations Density 0.002%

    No Known Activations