© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 69811
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to signal processing and acoustic analysis

    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
     Gra
    -0.07
    aped
    -0.07
     Burton
    -0.06
    Seed
    -0.06
     Lub
    -0.06
     exc
    -0.06
     Fit
    -0.06
     ti
    -0.06
     unknown
    -0.06
    à¸Ĺ
    -0.06
    POSITIVE LOGITS
    aphael
    0.07
    ãĥªãĤ«
    0.06
    ingleton
    0.06
    itech
    0.06
    ses
    0.06
    inaire
    0.06
    iples
    0.06
    ÑĢог
    0.06
     повин
    0.06
    ibold
    0.06
    Activations Density 0.152%

    No Known Activations