© 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. 104131
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions of becoming or joining with a group or an organization

    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
    ged
    -0.07
    .truth
    -0.07
    ساÙĨÛĮ
    -0.06
     Klein
    -0.06
    ÑĢаÑģ
    -0.06
     Horny
    -0.06
    opak
    -0.06
    ÑĢоÑĪ
    -0.06
    å¸Ń
    -0.06
    gaard
    -0.06
    POSITIVE LOGITS
    ublisher
    0.07
    /assert
    0.07
    _FOREACH
    0.07
    CAPE
    0.06
     Iterable
    0.06
    ich
    0.06
     consensus
    0.06
    μεÏģ
    0.06
    closure
    0.06
    ä¾Ľ
    0.06
    Activations Density 0.013%

    No Known Activations