© 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. 121570
    Prev
    Next
    INDEX
    Explanations

    expressions of intensity or degree, particularly focusing on the word "much."

    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
    rone
    -0.06
    -0.06
     Duffy
    -0.06
    rc
    -0.06
    its
    -0.06
     which
    -0.06
     Marcus
    -0.06
    ÄĽti
    -0.05
    asal
    -0.05
     Ñıке
    -0.05
    POSITIVE LOGITS
    ToOne
    0.08
    APPER
    0.07
    bmp
    0.07
    anners
    0.07
    kee
    0.07
    endar
    0.07
    \Id
    0.07
    .assets
    0.07
    STITUTE
    0.07
    KeyType
    0.07
    Activations Density 0.006%

    No Known Activations