© 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. 2553
    Prev
    Next
    INDEX
    Explanations

    positive affirmations and expressions of understanding related to personal experiences

    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
    ัà¸ķà¸ĸ
    -0.07
    èĭ¥
    -0.07
    ÑĢиг
    -0.06
    á»Ļn
    -0.06
    amburger
    -0.06
    pyx
    -0.06
    witter
    -0.06
    arges
    -0.06
    urer
    -0.06
    stup
    -0.06
    POSITIVE LOGITS
     ever
    0.09
    ever
    0.08
    urm
    0.07
     otherwise
    0.07
    athi
    0.07
    577
    0.07
     denn
    0.06
     вдÑĢÑĥг
    0.06
     lifetime
    0.06
    ones
    0.06
    Activations Density 0.062%

    No Known Activations