© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    adjectives describing size or scale

    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
     ------>
    -0.07
    айÑĤ
    -0.07
    εί
    -0.07
    bjerg
    -0.07
     Sabb
    -0.07
    iry
    -0.07
    iedy
    -0.07
    обÑĢаз
    -0.07
    è°ĥ
    -0.07
    ioned
    -0.07
    POSITIVE LOGITS
    ainer
    0.06
     level
    0.06
    gers
    0.06
    946
    0.06
    ened
    0.05
    -sized
    0.05
    estre
    0.05
    ç´ļ
    0.05
    -scale
    0.05
    od
    0.05
    Activations Density 0.004%

    No Known Activations