© 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. 62931
    Prev
    Next
    INDEX
    Explanations

    expressions indicating clarity or visibility of concepts

    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
    ød
    -0.07
    loth
    -0.06
     homeless
    -0.06
     exact
    -0.06
    law
    -0.06
    ®
    -0.06
    kir
    -0.06
    imer
    -0.06
    èµ·ãģĵ
    -0.06
    ood
    -0.06
    POSITIVE LOGITS
     throughout
    0.08
    adele
    0.07
     when
    0.07
    ropa
    0.07
    oldt
    0.07
    icode
    0.07
     mastur
    0.07
    sthrough
    0.06
     horizon
    0.06
    ignum
    0.06
    Activations Density 0.016%

    No Known Activations