© 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. 31618
    Prev
    Next
    INDEX
    Explanations

    references to various forms of intelligence or academic-related themes

    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
     unp
    -0.06
    L
    -0.06
    -
    -0.06
    /current
    -0.06
     (
    -0.06
     Alonso
    -0.06
     neither
    -0.06
    R
    -0.06
    :
    -0.06
    âĢİ
    -0.06
    POSITIVE LOGITS
    -centric
    0.11
    -Based
    0.11
    alone
    0.10
    ãģ°ãģĭãĤĬ
    0.10
    -only
    0.10
    -centered
    0.10
     Alone
    0.10
    _based
    0.10
    -based
    0.10
    -focused
    0.10
    Activations Density 0.094%

    No Known Activations