© 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. 29444
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    id
    -0.06
    uled
    -0.06
     interest
    -0.06
    ulet
    -0.05
    v
    -0.05
    lsen
    -0.05
     esp
    -0.05
     form
    -0.05
     $
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    (æ°´
    0.08
     gezocht
    0.07
    .her
    0.07
    ãĤ«ãĥĨãĤ´ãĥª
    0.07
    Ïĩη
    0.07
     nackte
    0.07
    eyse
    0.07
    SharedPtr
    0.07
    .Screen
    0.07
    .apps
    0.07
    Activations Density 0.015%

    No Known Activations