© 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. 121642
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and optimization constraints

    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
     att
    -0.06
     doom
    -0.06
     chung
    -0.06
     Trick
    -0.06
    orce
    -0.06
     unread
    -0.06
     my
    -0.06
    askan
    -0.05
    gle
    -0.05
     tit
    -0.05
    POSITIVE LOGITS
     preferably
    0.11
     ability
    0.10
    must
    0.08
     khả
    0.08
     MUST
    0.08
    ability
    0.08
    Must
    0.08
    Łèĥ½
    0.08
     must
    0.08
    prefer
    0.08
    Activations Density 0.025%

    No Known Activations