© 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. 39452
    Prev
    Next
    INDEX
    Explanations

    emotions related to change and personal struggle

    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
    ãĥ¼ãĤ¿ãĥ¼
    -0.07
    rame
    -0.06
    oub
    -0.06
    lg
    -0.06
     Grass
    -0.06
     Vend
    -0.06
    rets
    -0.06
    ÑĪкÑĥ
    -0.06
     duel
    -0.06
    sonian
    -0.06
    POSITIVE LOGITS
     throughout
    0.10
     Throughout
    0.09
    Throughout
    0.09
     déjÃł
    0.08
    ä¸įæĸŃ
    0.07
     lately
    0.07
    ä¸ĢæŃ¥
    0.07
    à¸ķลà¸Ńà¸Ķ
    0.07
     already
    0.07
    acci
    0.07
    Activations Density 0.049%

    No Known Activations