© 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. 17-LLAMASCOPE-RES-131K
    11. 5344
    Prev
    Next
    INDEX
    Explanations

    terminology related to scientific research methodologies and technologies

    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
    exels
    -0.07
    ε
    -0.07
    dra
    -0.06
     Fee
    -0.06
    еÑĢÑĤа
    -0.06
    aws
    -0.06
     formulas
    -0.06
    leen
    -0.06
     Prism
    -0.06
    aster
    -0.06
    POSITIVE LOGITS
    aper
    0.07
    Choices
    0.07
    ümÃ¼ÅŁ
    0.06
    SHARE
    0.06
    år
    0.06
    Ы
    0.06
    .postMessage
    0.06
     philosophy
    0.06
     поб
    0.06
    crew
    0.06
    Activations Density 0.010%

    No Known Activations