© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84897
    Prev
    Next
    INDEX
    Explanations

    specific terms related to speaker design and acoustics

    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
    paque
    -0.07
    keley
    -0.07
    ombo
    -0.07
    pike
    -0.07
    itchen
    -0.06
    pees
    -0.06
     comple
    -0.06
    arkin
    -0.06
    482
    -0.06
    771
    -0.06
    POSITIVE LOGITS
    TD
    0.07
    ÐĦ
    0.06
    ırak
    0.06
     pornstar
    0.06
    (inner
    0.06
    _SYNC
    0.06
    Å¡ov
    0.06
     Klopp
    0.06
    actionDate
    0.06
     sóc
    0.06
    Activations Density 0.015%

    No Known Activations