© 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. 76448
    Prev
    Next
    INDEX
    Explanations

    references to events and RSVPs

    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
    azzi
    -0.07
    adian
    -0.07
    ÃŃnÄĽ
    -0.06
    Å¡il
    -0.06
     Alternate
    -0.06
    meli
    -0.06
     æ¼
    -0.06
    aison
    -0.06
    sons
    -0.06
    uestas
    -0.06
    POSITIVE LOGITS
    arer
    0.07
     Comet
    0.06
     Doch
    0.06
    ãĥ¼ãĥľ
    0.06
    opoulos
    0.06
    ambah
    0.06
    unky
    0.06
    _sqrt
    0.06
     Dak
    0.06
     veteran
    0.06
    Activations Density 0.002%

    No Known Activations