© 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. 119271
    Prev
    Next
    INDEX
    Explanations

    references to conclusions or summaries

    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
    .Keyboard
    -0.07
     Mits
    -0.07
    lena
    -0.07
    Ð¡Ðł
    -0.07
    esi
    -0.06
    ulp
    -0.06
     Bold
    -0.06
    ockey
    -0.06
     èµ
    -0.06
     Gä
    -0.06
    POSITIVE LOGITS
    .LayoutStyle
    0.08
    :
    0.07
    chin
    0.06
    /core
    0.06
    oldown
    0.06
    ict
    0.06
    Bottom
    0.06
    obutton
    0.06
     bottom
    0.06
     folders
    0.06
    Activations Density 0.003%

    No Known Activations