© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89806
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivation and factors influencing behavior

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    fidf
    -0.07
    imeline
    -0.07
    timeline
    -0.07
    ifestyles
    -0.06
     etm
    -0.06
    esimal
    -0.06
    abox
    -0.06
    iteli
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    åī£
    -0.06
    POSITIVE LOGITS
    .Fat
    0.07
    agi
    0.07
     task
    0.07
    apel
    0.07
     productivity
    0.06
     tasks
    0.06
     Nap
    0.06
     Fat
    0.06
     Tasks
    0.06
    hift
    0.06
    Activations Density 0.000%

    No Known Activations