© 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. 121355
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ease or simplicity in tasks or processes

    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
    ÏĢο
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    öl
    -0.07
    angent
    -0.07
    .mixin
    -0.07
    .openapi
    -0.07
    ssh
    -0.07
     Kız
    -0.07
    sock
    -0.07
    ellen
    -0.06
    POSITIVE LOGITS
    -than
    0.11
     than
    0.10
    than
    0.09
    _than
    0.08
     THAN
    0.08
     dÃłng
    0.08
     Than
    0.07
     než
    0.07
    /qu
    0.07
     easier
    0.07
    Activations Density 0.010%

    No Known Activations