© 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. 14166
    Prev
    Next
    INDEX
    Explanations

    ellipses and interruptions in text, indicating pauses or omitted content

    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
     Khu
    -0.08
    sher
    -0.08
    IVED
    -0.07
     biá»ĥu
    -0.07
    monds
    -0.07
    mayan
    -0.07
     lá»Ļ
    -0.07
    oftware
    -0.07
    .tell
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
    aa
    0.07
    aram
    0.07
    orse
    0.06
    abis
    0.06
    ava
    0.05
    als
    0.05
    zy
    0.05
    aaaa
    0.05
    0.05
     controller
    0.05
    Activations Density 0.008%

    No Known Activations