© 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. 94929
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating levels of creativity or mental health conditions

    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
    .Generation
    -0.07
    abit
    -0.07
    .cls
    -0.07
    asm
    -0.07
    ETO
    -0.07
    ãģıãĤĵ
    -0.07
     Toro
    -0.07
     æģ
    -0.07
    achat
    -0.06
    ãĥ³ãĥī
    -0.06
    POSITIVE LOGITS
     than
    0.07
     likely
    0.07
    'http
    0.06
     Baum
    0.06
     overall
    0.06
     nearly
    0.06
     to
    0.06
    iye
    0.06
    HttpException
    0.06
     pro
    0.06
    Activations Density 0.016%

    No Known Activations