© 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. 18846
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright infringement and ownership issues

    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
    ocy
    -0.07
     sig
    -0.07
     Sig
    -0.06
    ç°
    -0.06
    hem
    -0.06
    [code
    -0.06
     Signing
    -0.06
     pitch
    -0.06
    rupt
    -0.06
    raphics
    -0.06
    POSITIVE LOGITS
    ugo
    0.07
     Content
    0.07
    kke
    0.07
    keterangan
    0.07
    ektor
    0.06
     infr
    0.06
    sez
    0.06
     McGr
    0.06
    Content
    0.06
     protected
    0.06
    Activations Density 0.002%

    No Known Activations