© 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. 53770
    Prev
    Next
    INDEX
    Explanations

    references to historical and cultural subjects

    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
    ži
    -0.07
    Ïĩη
    -0.07
    hei
    -0.06
    éĤª
    -0.06
    emaker
    -0.06
    akra
    -0.06
    cies
    -0.06
     Wilderness
    -0.06
    æķ·
    -0.06
    Compiled
    -0.06
    POSITIVE LOGITS
     crit
    0.07
    _crit
    0.07
     literature
    0.07
    .Unicode
    0.07
     metre
    0.07
    ÙĪاÙĩ
    0.07
    MASK
    0.06
    illon
    0.06
     meters
    0.06
     Meter
    0.06
    Activations Density 0.155%

    No Known Activations