© 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. 9-LLAMASCOPE-RES-131K
    11. 99024
    Prev
    Next
    INDEX
    Explanations

    terms related to progress and ongoing projects

    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
    еÑĢÑĤа
    -0.07
    Interstitial
    -0.06
     ancest
    -0.06
    uhl
    -0.06
    ScreenState
    -0.06
    лÑıÑİÑĤ
    -0.06
     straight
    -0.06
    lee
    -0.06
    culos
    -0.06
    alm
    -0.06
    POSITIVE LOGITS
    Cab
    0.07
     Cab
    0.07
     Kem
    0.06
    amins
    0.06
    ãģĹãģ¦ãĤĭ
    0.06
    .wall
    0.06
    à¹īà¸Ńà¸Ļ
    0.06
     Minute
    0.06
    .beh
    0.06
    OLT
    0.06
    Activations Density 0.017%

    No Known Activations