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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71871
    Prev
    Next
    INDEX
    Explanations

    information related to professional qualifications and legal expertise

    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
    rescia
    -0.08
     Serg
    -0.07
    лава
    -0.07
    #ad
    -0.07
    aju
    -0.07
     Evet
    -0.06
    éĤ¦
    -0.06
    romosome
    -0.06
    rof
    -0.06
     fkk
    -0.06
    POSITIVE LOGITS
     extern
    0.08
     intern
    0.07
    иÑĢов
    0.06
     Manufacturers
    0.06
    intern
    0.06
    à¥Īद
    0.06
    ymoon
    0.05
     Intern
    0.05
    zahl
    0.05
    erk
    0.05
    Activations Density 0.008%

    No Known Activations