© 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. 89210
    Prev
    Next
    INDEX
    Explanations

    references to programming or coding elements, particularly related to Python packages

    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
    ãĥ¼ãĥª
    -0.07
    anya
    -0.07
    portlet
    -0.06
    èĺ
    -0.06
    claimer
    -0.06
    pering
    -0.06
    oya
    -0.06
    sch
    -0.06
    emez
    -0.06
    !*
    -0.06
    POSITIVE LOGITS
    @testable
    0.06
    PressEvent
    0.06
     diret
    0.06
    ηγ
    0.06
     Hanna
    0.06
     vois
    0.06
    Nullable
    0.06
    Typed
    0.06
    omitempty
    0.06
     Butter
    0.06
    Activations Density 0.000%

    No Known Activations