© 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. 63049
    Prev
    Next
    INDEX
    Explanations

    artistic expressions involving mixed media and unconventional materials

    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
    ingham
    -0.07
    ê´ij
    -0.07
    ýš
    -0.07
    tridge
    -0.07
    коÑĤ
    -0.07
     ков
    -0.07
    rocket
    -0.06
    nett
    -0.06
    etten
    -0.06
    rito
    -0.06
    POSITIVE LOGITS
    kontakte
    0.07
    /Grid
    0.07
     collected
    0.06
    æĤī
    0.06
    icamente
    0.06
    bob
    0.06
    اÙģÙĬØ©
    0.06
     Obr
    0.06
    162
    0.06
     Liberties
    0.06
    Activations Density 0.022%

    No Known Activations