© 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. 9-LLAMASCOPE-RES-131K
    11. 94133
    Prev
    Next
    INDEX
    Explanations

    various forms and related concepts of labels, tags, and stickers

    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
    inne
    -0.06
    .ht
    -0.06
     surf
    -0.06
    elia
    -0.06
    estone
    -0.05
     optim
    -0.05
     Bien
    -0.05
    ãĤĴãģĬ
    -0.05
    -0.05
     SaÄŁ
    -0.05
    POSITIVE LOGITS
    Ñģий
    0.07
    utron
    0.07
    .useState
    0.07
    à¹ĭ
    0.07
    ncmp
    0.07
    #
    0.06
    .TabIndex
    0.06
    erece
    0.06
    ÙħÙĦÙĥØ©
    0.06
     بÙĨد
    0.06
    Activations Density 0.004%

    No Known Activations