© 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. 1162
    Prev
    Next
    INDEX
    Explanations

    inquiries about personal experiences and recommendations

    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
    ustos
    -0.06
    plevel
    -0.06
    inston
    -0.06
    æŁ³
    -0.06
    лем
    -0.06
    ervo
    -0.06
    ald
    -0.06
    sic
    -0.06
    ADOS
    -0.06
    åĽ
    -0.05
    POSITIVE LOGITS
     nhé
    0.07
    295
    0.07
    ëĿ½
    0.07
     below
    0.06
    outu
    0.06
    below
    0.06
     Kirk
    0.06
    iton
    0.06
    cale
    0.06
    Ľi
    0.06
    Activations Density 0.012%

    No Known Activations