© 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. 15-LLAMASCOPE-RES-131K
    11. 87966
    Prev
    Next
    INDEX
    Explanations

    terms related to acoustic engineering and microphone technology

    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
    ruit
    -0.07
    ÌĨ
    -0.06
     Ag
    -0.06
    emain
    -0.06
    //{{
    -0.06
    agenta
    -0.06
     Beng
    -0.06
     aggreg
    -0.06
    ÑĦи
    -0.06
    eward
    -0.06
    POSITIVE LOGITS
     unequal
    0.09
     khác
    0.09
     different
    0.08
    ä¸įåIJĮçļĦ
    0.08
    different
    0.08
     différent
    0.07
    -Speed
    0.07
     uneven
    0.07
    une
    0.07
     differential
    0.07
    Activations Density 0.058%

    No Known Activations