© 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. 27033
    Prev
    Next
    INDEX
    Explanations

    actions related to processing and manipulating data or objects

    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
    andan
    -0.07
    .gwt
    -0.06
     nÃło
    -0.06
    zek
    -0.06
    si
    -0.06
    imu
    -0.06
    AWN
    -0.06
    nik
    -0.06
    ITCH
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
     it
    0.16
     them
    0.15
    å®ĥ们
    0.11
     ê·¸ê²ĥ
    0.10
    them
    0.10
    å®ĥ
    0.10
    ãģĿãĤĮãģ¯
    0.09
     its
    0.09
     they
    0.09
     itu
    0.09
    Activations Density 0.065%

    No Known Activations