© 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. 31615
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and syntax

    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
     pinterest
    -0.09
    eden
    -0.07
    dale
    -0.07
    getJSON
    -0.07
    oria
    -0.07
    ainless
    -0.07
    .realm
    -0.07
    ventus
    -0.07
    askell
    -0.07
    kü
    -0.07
    POSITIVE LOGITS
     equivalent
    0.07
    Fallback
    0.07
     older
    0.06
    MOTE
    0.06
    achat
    0.06
    inium
    0.06
    ystack
    0.06
     antiqu
    0.06
    _old
    0.06
     styl
    0.06
    Activations Density 0.006%

    No Known Activations