© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74639
    Prev
    Next
    INDEX
    Explanations

    specifications or references related to technology and electronics

    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
    antino
    -0.07
    öyle
    -0.07
    ÑĶм
    -0.06
    á»ı
    -0.06
    adir
    -0.06
    ysz
    -0.06
    apos
    -0.06
    igli
    -0.06
    ams
    -0.06
    adio
    -0.06
    POSITIVE LOGITS
     Fol
    0.06
     KT
    0.06
    474
    0.06
    952
    0.06
    ield
    0.06
    tal
    0.06
    âĸĪâĸĪ
    0.06
    026
    0.06
    628
    0.06
    390
    0.06
    Activations Density 0.010%

    No Known Activations