© 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. 123294
    Prev
    Next
    INDEX
    Explanations

    specific acronyms or abbreviations related to technology and medical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    igsaw
    -0.08
    acf
    -0.07
    adays
    -0.07
    jamin
    -0.07
    odore
    -0.07
    rador
    -0.07
     aforementioned
    -0.07
    foundland
    -0.07
    wealth
    -0.07
    sgiving
    -0.07
    POSITIVE LOGITS
    oret
    0.12
    ories
    0.09
    owing
    0.09
    cing
    0.09
    itionally
    0.08
    ronic
    0.08
     ведÑĮ
    0.08
    waiting
    0.08
    pecially
    0.08
    iming
    0.08
    Activations Density 0.125%

    No Known Activations