© 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. 9-LLAMASCOPE-RES-131K
    11. 95739
    Prev
    Next
    INDEX
    Explanations

    the word "by" indicating action or agency in sentences

    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
    voj
    -0.06
    allen
    -0.06
    ussen
    -0.06
    nts
    -0.06
    aight
    -0.06
    ught
    -0.06
    æĺ¯åIJ¦
    -0.06
     isize
    -0.06
    ughter
    -0.06
    izoph
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    opic
    0.07
    ared
    0.07
    alion
    0.07
    iba
    0.06
    /slick
    0.06
    PEC
    0.06
    rost
    0.06
    olan
    0.06
    idi
    0.06
    Activations Density 0.054%

    No Known Activations