© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    references to significant components or elements within a context

    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
    «a
    -0.07
    och
    -0.06
    ve
    -0.06
    à¤ķरण
    -0.06
    bz
    -0.06
    ikki
    -0.06
     **************************************************************************
    -0.06
    ien
    -0.06
     anyways
    -0.06
    iol
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    anter
    0.07
    131
    0.07
    herits
    0.07
    camel
    0.06
    771
    0.06
    483
    0.06
    144
    0.06
    oldown
    0.06
    862
    0.06
    Activations Density 0.001%

    No Known Activations