© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    references to training and practical experience in a professional 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
     chairman
    -0.08
    idle
    -0.07
    ama
    -0.07
    oi
    -0.06
     virtually
    -0.06
    onz
    -0.06
     its
    -0.06
    idis
    -0.06
     rejection
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
    _mC
    0.09
    каÑģ
    0.08
    906
    0.07
    AdapterManager
    0.07
    eczy
    0.07
    _tC
    0.07
     Zaman
    0.07
    piar
    0.07
    ourcem
    0.07
    RuntimeObject
    0.07
    Activations Density 0.000%

    No Known Activations