© 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. 73638
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to changes and adjustments in products

    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
    illez
    -0.07
    moduleId
    -0.07
    ntag
    -0.07
    bsub
    -0.07
    elman
    -0.07
    oger
    -0.07
    clc
    -0.06
    urum
    -0.06
     soon
    -0.06
    addock
    -0.06
    POSITIVE LOGITS
     вд
    0.06
    akers
    0.06
     Wis
    0.06
    غة
    0.06
    çłĤ
    0.06
    Ľ
    0.06
     Appearance
    0.06
     ли
    0.06
     here
    0.06
     resulted
    0.06
    Activations Density 0.031%

    No Known Activations