© 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. 29045
    Prev
    Next
    INDEX
    Explanations

    user credentials and associated information

    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
    ossa
    -0.06
    uard
    -0.06
    utow
    -0.06
    stin
    -0.06
    xfff
    -0.06
    vä
    -0.06
    .aspx
    -0.05
    amide
    -0.05
     Preis
    -0.05
    Â
    -0.05
    POSITIVE LOGITS
    123
    0.09
    interop
    0.07
    rollback
    0.07
    еÑĤÑĮ
    0.07
    isman
    0.06
    .Localization
    0.06
    eltas
    0.06
    098
    0.06
     Stateless
    0.06
     backlight
    0.06
    Activations Density 0.007%

    No Known Activations