© 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. 56086
    Prev
    Next
    INDEX
    Explanations

    instances of "description" and "question" labels in the text

    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
    ows
    -0.07
    adden
    -0.07
    éĺµ
    -0.06
    ebo
    -0.06
    fen
    -0.06
    unds
    -0.06
     tern
    -0.06
    ucene
    -0.06
    견
    -0.06
    bull
    -0.06
    POSITIVE LOGITS
    agus
    0.06
    idia
    0.06
    ."&
    0.06
    alling
    0.06
    ÙĬا
    0.06
    ìĽĥ
    0.06
    Ñĥда
    0.06
    ذا
    0.06
    lox
    0.06
     queryInterface
    0.06
    Activations Density 0.001%

    No Known Activations