© 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. 14204
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "lack" or insufficiency in various contexts

    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
    ulk
    -0.07
    issen
    -0.07
    izable
    -0.07
    _callable
    -0.07
    á»ħ
    -0.06
    agedList
    -0.06
     ==============================================================
    -0.06
    лож
    -0.06
    authenticated
    -0.06
     ÙĨار
    -0.06
    POSITIVE LOGITS
    ada
    0.09
    y
    0.08
    ãĥ¼ãĥī
    0.08
    itecture
    0.07
    full
    0.07
    ily
    0.07
    nowled
    0.07
    lust
    0.06
    148
    0.06
    ade
    0.06
    Activations Density 0.012%

    No Known Activations