© 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. 92619
    Prev
    Next
    INDEX
    Explanations

    adverbs that modify manner or degree

    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
    rubu
    -0.07
     TRACE
    -0.07
    ityEngine
    -0.07
    âĶ£
    -0.07
    :variables
    -0.07
    OMPI
    -0.07
     ÙĨÛĮر
    -0.07
    ebe
    -0.07
     Redistributions
    -0.06
    Orm
    -0.06
    POSITIVE LOGITS
    erer
    0.08
     Tou
    0.06
    atta
    0.06
     commercial
    0.06
     Faction
    0.06
    ór
    0.06
    amb
    0.06
    å¦
    0.06
     же
    0.06
    regon
    0.06
    Activations Density 0.000%

    No Known Activations