© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86412
    Prev
    Next
    INDEX
    Explanations

    mentions of "dro," which appears to be a recurring theme or term in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    noinspection
    -0.07
    ÎŃν
    -0.07
    ners
    -0.06
    RequestMethod
    -0.06
    \/\/
    -0.06
    ergus
    -0.06
    ENO
    -0.06
    isen
    -0.06
    adece
    -0.06
    _Interface
    -0.06
    POSITIVE LOGITS
     dro
    0.11
     Dro
    0.09
    dro
    0.08
    æ¢ģ
    0.07
    TM
    0.07
    zier
    0.07
    plet
    0.07
    indi
    0.06
    aming
    0.06
     swo
    0.06
    Activations Density 0.007%

    No Known Activations