© 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. 59476
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data points

    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
     terminal
    -0.07
    terminal
    -0.07
     stri
    -0.06
    erland
    -0.06
    Porn
    -0.06
    alis
    -0.06
    wright
    -0.06
    )application
    -0.06
     loos
    -0.05
     pars
    -0.05
    POSITIVE LOGITS
    ếp
    0.07
    há
    0.07
    ylko
    0.07
     Farms
    0.07
    alendar
    0.06
     ucwords
    0.06
    루
    0.06
    outil
    0.06
    ÙĬÙĨÙĩ
    0.06
    ÌĤ
    0.06
    Activations Density 0.000%

    No Known Activations