© 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. 30525
    Prev
    Next
    INDEX
    Explanations

    themes related to personal development and motivation

    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
    aku
    -0.07
    .ServiceModel
    -0.06
    nej
    -0.06
    /drivers
    -0.06
    uche
    -0.06
     tez
    -0.06
    _ALIGNMENT
    -0.06
    DDD
    -0.06
    ë¹Į
    -0.06
     ustanov
    -0.06
    POSITIVE LOGITS
     rewards
    0.08
     reward
    0.07
     Reward
    0.07
     éĸ¢éĢ£
    0.07
     mn
    0.06
     Rewards
    0.06
    udo
    0.06
    avad
    0.06
     auditing
    0.06
     authoritative
    0.06
    Activations Density 0.033%

    No Known Activations