© 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. 91521
    Prev
    Next
    INDEX
    Explanations

    HTML and document structure-related elements

    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
    ertext
    -0.09
    lint
    -0.08
    eview
    -0.07
    eut
    -0.07
    .scalablytyped
    -0.07
    ookie
    -0.07
    ıma
    -0.07
    ooke
    -0.07
    äºĭåĭĻ
    -0.07
    esan
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.07
     Kup
    0.07
    owitz
    0.07
    gate
    0.06
    icity
    0.06
    ellan
    0.06
    -sized
    0.05
     Bowman
    0.05
    ↵
    0.05
    licate
    0.05
    Activations Density 0.000%

    No Known Activations