© 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. 80784
    Prev
    Next
    INDEX
    Explanations

    expressions of awareness or understanding 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
    ÑĨвеÑĤ
    -0.07
    REA
    -0.07
    wik
    -0.07
     Äijạo
    -0.07
    uary
    -0.06
    rei
    -0.06
    ember
    -0.06
    omez
    -0.06
    reme
    -0.06
    rand
    -0.06
    POSITIVE LOGITS
    ness
    0.10
     of
    0.09
    ingly
    0.08
    fulness
    0.08
    NESS
    0.08
    ırak
    0.07
    lessly
    0.07
    /alert
    0.07
    454
    0.07
     about
    0.07
    Activations Density 0.010%

    No Known Activations