© 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. 130990
    Prev
    Next
    INDEX
    Explanations

    structured data and technical specifications

    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
    acre
    -0.06
     Äijình
    -0.06
    rites
    -0.06
    stell
    -0.06
    ulton
    -0.06
     Adler
    -0.06
     ni
    -0.06
    ips
    -0.06
     cref
    -0.06
    ManagerInterface
    -0.06
    POSITIVE LOGITS
    AGMENT
    0.07
    zano
    0.07
    cy
    0.07
    zym
    0.07
    ãĥ¼ãĥĸ
    0.06
    027
    0.06
    λÏħ
    0.06
    vez
    0.06
    orum
    0.06
    raison
    0.06
    Activations Density 0.044%

    No Known Activations