© 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. 69012
    Prev
    Next
    INDEX
    Explanations

    significant events or entities 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
    rvé
    -0.06
     similarly
    -0.05
    centration
    -0.05
    hiro
    -0.05
    _GRP
    -0.05
    tri
    -0.05
    ãģ¾ãģļ
    -0.05
     dia
    -0.05
    ‘
    -0.05
    iox
    -0.05
    POSITIVE LOGITS
     thus
    0.08
     cul
    0.08
    ynos
    0.07
    Unnamed
    0.07
    cul
    0.07
    xmm
    0.07
    LANG
    0.07
    ÃĵN
    0.07
    æıĽ
    0.07
    layan
    0.07
    Activations Density 0.043%

    No Known Activations