© 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. 18534
    Prev
    Next
    INDEX
    Explanations

    references to food and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ledon
    -0.07
     leak
    -0.06
    Soup
    -0.06
    alan
    -0.06
     tun
    -0.06
    .scalablytyped
    -0.06
     tight
    -0.06
     Catalyst
    -0.06
    ableView
    -0.06
     offline
    -0.06
    POSITIVE LOGITS
    icol
    0.07
    ارات
    0.07
    867
    0.07
    rep
    0.07
     Ñĥд
    0.07
     pii
    0.06
    ãĥīãĥ«
    0.06
    ombies
    0.06
    ãģĭãģij
    0.06
     vom
    0.06
    Activations Density 0.046%

    No Known Activations