© 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. 38554
    Prev
    Next
    INDEX
    Explanations

    concepts related to expertise and the effort required to achieve it

    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
     Holt
    -0.07
     Fon
    -0.07
     grav
    -0.06
    tener
    -0.06
    اØ
    -0.06
     noir
    -0.06
    inker
    -0.06
    åĢ«
    -0.06
    asil
    -0.06
     zast
    -0.06
    POSITIVE LOGITS
     skill
    0.08
     training
    0.07
    Prod
    0.07
     learning
    0.07
     Skill
    0.07
    learning
    0.07
     Talent
    0.07
     talent
    0.07
     repetition
    0.07
    -learning
    0.07
    Activations Density 0.012%

    No Known Activations