© 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. 123457
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate structure and private organizations

    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
    avirus
    -0.07
    friend
    -0.06
    cratch
    -0.06
    oa
    -0.06
    mour
    -0.06
    -0.06
     shorthand
    -0.06
    arius
    -0.06
    eting
    -0.06
    fred
    -0.05
    POSITIVE LOGITS
    AAF
    0.07
    ê
    0.07
    аÑĤки
    0.07
    urtle
    0.07
    amm
    0.07
    senal
    0.07
    _exc
    0.07
     blackColor
    0.07
    æ°§
    0.07
    UFFER
    0.07
    Activations Density 0.001%

    No Known Activations