© 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. 9-LLAMASCOPE-RES-131K
    11. 98994
    Prev
    Next
    INDEX
    Explanations

    references to formatting or encoding standards

    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
    azzi
    -0.08
    ãĥ¼ãĥ
    -0.06
    alla
    -0.06
     Limits
    -0.06
     limits
    -0.06
    .Autowired
    -0.06
    anut
    -0.06
    549
    -0.06
    uce
    -0.06
    Limits
    -0.06
    POSITIVE LOGITS
    strap
    0.07
    uw
    0.07
    kud
    0.07
    earer
    0.06
    ÑĢÑĥд
    0.06
     fitte
    0.06
    ilder
    0.06
    å«Į
    0.06
    langs
    0.06
    KS
    0.06
    Activations Density 0.000%

    No Known Activations