© 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. 120545
    Prev
    Next
    INDEX
    Explanations

    references to writing and creative professions

    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
    IEW
    -0.07
    owell
    -0.07
    ÐŀÐĿ
    -0.06
     Bounds
    -0.06
    apes
    -0.06
    rogram
    -0.06
     sophistic
    -0.06
    Conf
    -0.05
    ków
    -0.05
     rok
    -0.05
    POSITIVE LOGITS
     write
    0.07
    æĬ¥éģĵ
    0.07
    presso
    0.07
     stories
    0.07
    /write
    0.07
    稿
    0.07
     news
    0.07
     story
    0.07
     article
    0.07
    inate
    0.06
    Activations Density 0.014%

    No Known Activations