© 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. 108723
    Prev
    Next
    INDEX
    Explanations

    references to greatness or notable individuals

    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
    ican
    -0.07
    abin
    -0.07
    abinet
    -0.06
    ëĿ¼ëĬĶ
    -0.06
    ALER
    -0.06
    PageIndex
    -0.06
    ất
    -0.06
    untime
    -0.06
     ActiveSupport
    -0.06
    aler
    -0.06
    POSITIVE LOGITS
    -grand
    0.10
    atsby
    0.09
    coat
    0.09
    sword
    0.08
    eur
    0.08
    (est
    0.07
    s
    0.07
    333
    0.06
     migration
    0.06
     majority
    0.06
    Activations Density 0.014%

    No Known Activations