© 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. 121354
    Prev
    Next
    INDEX
    Explanations

    expressions related to prioritizing responsibilities or desires

    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
    VID
    -0.07
    ä
    -0.06
    ipel
    -0.06
    steam
    -0.06
    anst
    -0.06
     Anim
    -0.06
    yu
    -0.06
    ertz
    -0.06
    porte
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
     emphasis
    0.08
    aroo
    0.07
    emphasis
    0.07
     utilisateur
    0.07
     interests
    0.06
     welfare
    0.06
     pedal
    0.06
    arat
    0.06
     concerns
    0.06
    gree
    0.06
    Activations Density 0.011%

    No Known Activations