© 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. 63258
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "to be" in various forms

    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
    enance
    -0.07
    -0.07
     ово
    -0.06
    REDENTIAL
    -0.06
     både
    -0.06
    ensen
    -0.06
    etto
    -0.06
    itech
    -0.06
    _rt
    -0.06
    ãĢģ
    -0.06
    POSITIVE LOGITS
     subsequently
    0.07
    eut
    0.07
    olan
    0.07
    Ïģκ
    0.07
    eding
    0.07
    jos
    0.07
     consequently
    0.06
    xious
    0.06
     downright
    0.06
     possibly
    0.06
    Activations Density 0.027%

    No Known Activations