© 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. 69002
    Prev
    Next
    INDEX
    Explanations

    terms related to specific individuals or entities, particularly those associated with the name "Rhonda" and variations thereof

    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
    åij½
    -0.08
    EZ
    -0.06
    449
    -0.06
    acity
    -0.06
    eck
    -0.06
    469
    -0.06
    @nate
    -0.06
    ress
    -0.06
    resses
    -0.06
    xFFF
    -0.06
    POSITIVE LOGITS
     Rh
    0.08
    annon
    0.07
    ÑĥкÑĤ
    0.07
    Rh
    0.07
    zik
    0.07
    ynch
    0.07
    اÙĪرÛĮ
    0.07
    chter
    0.07
    omba
    0.07
     Rhodes
    0.07
    Activations Density 0.018%

    No Known Activations