© 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. 63196
    Prev
    Next
    INDEX
    Explanations

    chapter or section references in a text

    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
    versions
    -0.06
     Picture
    -0.06
    .ToShort
    -0.06
     picture
    -0.06
    ematic
    -0.06
     Äijây
    -0.06
    ear
    -0.06
    arend
    -0.06
    оÑģк
    -0.06
    zk
    -0.06
    POSITIVE LOGITS
     titled
    0.08
    .scalablytyped
    0.07
    uras
    0.07
     عشر
    0.07
    ìłĪ
    0.07
    _literals
    0.07
    apos
    0.06
    agh
    0.06
    åı«
    0.06
    woke
    0.06
    Activations Density 0.024%

    No Known Activations