© 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. 63239
    Prev
    Next
    INDEX
    Explanations

    references to companies and business entities

    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
    Äħd
    -0.08
    OperationException
    -0.07
    acro
    -0.07
     equival
    -0.06
    kou
    -0.06
    igli
    -0.06
    erdem
    -0.06
    ÄĻ
    -0.06
    ukkan
    -0.06
     Ub
    -0.06
    POSITIVE LOGITS
     Inc
    0.09
     LLC
    0.09
    Inc
    0.09
     Ltd
    0.07
    _inc
    0.07
    LL
    0.07
    Ltd
    0.07
    lld
    0.06
     Farr
    0.06
    orp
    0.06
    Activations Density 0.021%

    No Known Activations