© 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. 56223
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio signal processing

    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
     pen
    -0.07
     some
    -0.06
     mark
    -0.06
    :
    -0.06
    one
    -0.06
     or
    -0.06
     anch
    -0.06
     standing
    -0.06
     ability
    -0.06
     Self
    -0.06
    POSITIVE LOGITS
    ην
    0.08
    senal
    0.08
    STREAM
    0.08
     pÅĻiv
    0.08
    oola
    0.08
    é¨
    0.08
    ActionCreators
    0.08
     dạng
    0.08
    -License
    0.08
    adem
    0.08
    Activations Density 0.148%

    No Known Activations