© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89577
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and data management

    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
    acle
    -0.07
    ayo
    -0.06
    427
    -0.06
    errar
    -0.06
    ypse
    -0.06
    ocha
    -0.06
    agr
    -0.06
    вÑĢоп
    -0.06
    <>
    -0.06
    cerr
    -0.06
    POSITIVE LOGITS
    olley
    0.07
     ideas
    0.07
     Submission
    0.07
     Ideas
    0.06
    Submit
    0.06
     pitching
    0.06
     submission
    0.06
    į¼
    0.06
    aque
    0.06
    ÏĮγ
    0.06
    Activations Density 0.000%

    No Known Activations