© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97682
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to signal processing and audio calibration

    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
     isize
    -0.06
    pig
    -0.06
    vous
    -0.06
    adel
    -0.06
     Pall
    -0.06
    вÑĢоп
    -0.06
    ntax
    -0.06
    ικα
    -0.06
    sha
    -0.06
    avig
    -0.06
    POSITIVE LOGITS
    enson
    0.07
    ãĥĭãĥ¼
    0.07
    bell
    0.07
     stretch
    0.06
    ä¸ģ
    0.06
     æĬķ稿
    0.06
     bell
    0.06
    磨
    0.06
    quier
    0.06
     tim
    0.06
    Activations Density 0.283%

    No Known Activations