© 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. 53738
    Prev
    Next
    INDEX
    Explanations

    mentions of fear and its various expressions

    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
    quirer
    -0.07
    anness
    -0.07
     POINTER
    -0.07
    onavir
    -0.07
    olare
    -0.07
    gere
    -0.07
    inea
    -0.07
    cxx
    -0.07
    gers
    -0.06
    Ñıз
    -0.06
    POSITIVE LOGITS
    lessly
    0.15
    fully
    0.11
    fulness
    0.10
     hã
    0.10
    ful
    0.09
    mong
    0.09
    full
    0.07
    æĢĸ
    0.07
    lessness
    0.07
    ably
    0.07
    Activations Density 0.012%

    No Known Activations