© 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. 91516
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers or dates

    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
     ÄĮer
    -0.07
    aze
    -0.06
    lando
    -0.06
     thrill
    -0.06
     o
    -0.06
    repid
    -0.06
    udiant
    -0.05
    lauf
    -0.05
    cash
    -0.05
    reaction
    -0.05
    POSITIVE LOGITS
    ÑĢÑĥкÑĤÑĥ
    0.07
    odox
    0.07
     наÑĢ
    0.07
    缸
    0.07
    oldemort
    0.07
    qli
    0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.06
    inkel
    0.06
     appendString
    0.06
    ê¶Į
    0.06
    Activations Density 0.001%

    No Known Activations