© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    terms related to quality, performance, and safety in products

    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
    oller
    -0.07
    cie
    -0.07
    iesz
    -0.07
     Ekim
    -0.06
     curse
    -0.06
    ysz
    -0.06
    aver
    -0.06
    avl
    -0.06
    IES
    -0.06
     gems
    -0.06
    POSITIVE LOGITS
    isle
    0.07
    Caption
    0.06
     thanks
    0.06
    thanks
    0.06
     Bor
    0.06
    lic
    0.06
    ught
    0.06
     dank
    0.06
    querque
    0.06
    URITY
    0.06
    Activations Density 0.023%

    No Known Activations