© 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. 124172
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to predictive language and inclusivity

    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
    essim
    -0.07
    cete
    -0.07
    ÙĨÙĬØ©
    -0.07
    ialect
    -0.07
    artisan
    -0.07
    _lex
    -0.06
     Spears
    -0.06
     ÎļÏħ
    -0.06
    -д
    -0.06
    eso
    -0.06
    POSITIVE LOGITS
    itzer
    0.06
     etc
    0.06
    uspend
    0.06
    athon
    0.06
    isis
    0.06
    itter
    0.06
     valor
    0.06
    Ñİ
    0.06
    öh
    0.06
    abler
    0.05
    Activations Density 0.001%

    No Known Activations