© 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. 123473
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and judicial actions

    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
    anie
    -0.06
    hole
    -0.06
     Wire
    -0.05
    VELO
    -0.05
    oma
    -0.05
     rank
    -0.05
    graded
    -0.05
     Interior
    -0.05
    IDGET
    -0.05
    of
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.09
    UrlParser
    0.08
    HeaderCode
    0.07
    statt
    0.07
    âĻª↵↵
    0.07
    mada
    0.07
    afil
    0.07
    :href
    0.07
    istica
    0.06
     thang
    0.06
    Activations Density 0.002%

    No Known Activations