© 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. 30237
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics related to demographics and households

    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
    hea
    -0.08
    inker
    -0.07
    attern
    -0.07
    uble
    -0.06
    ellas
    -0.06
    hetto
    -0.06
    rais
    -0.06
    brero
    -0.06
    andez
    -0.06
    ipl
    -0.06
    POSITIVE LOGITS
    _twitter
    0.07
    @qq
    0.07
     pol
    0.06
     ıs
    0.06
    uzzi
    0.06
    ocop
    0.06
    ugi
    0.06
    chin
    0.06
     Pump
    0.06
    /rss
    0.06
    Activations Density 0.004%

    No Known Activations