© 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. 89615
    Prev
    Next
    INDEX
    Explanations

    terms related to ease of use and efficiency

    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
    .shell
    -0.07
    facet
    -0.06
    hen
    -0.06
    unate
    -0.06
    undy
    -0.06
    ÑĢоÑĩ
    -0.06
    937
    -0.06
    oor
    -0.06
    ãn
    -0.06
    аÑĢÑĩ
    -0.06
    POSITIVE LOGITS
     without
    0.12
    without
    0.10
     WITHOUT
    0.10
     ohne
    0.10
     via
    0.10
     Without
    0.09
     senza
    0.08
     zonder
    0.08
    Without
    0.08
     ÏĩÏīÏģίÏĤ
    0.07
    Activations Density 0.021%

    No Known Activations