© 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. 121350
    Prev
    Next
    INDEX
    Explanations

    concepts related to computers and technology

    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
     observ
    -0.07
    uco
    -0.07
     Priv
    -0.06
     priv
    -0.06
     policy
    -0.06
     Kat
    -0.06
    ko
    -0.06
     Hab
    -0.06
    lector
    -0.06
     Ko
    -0.05
    POSITIVE LOGITS
     computer
    0.18
    computer
    0.17
     computers
    0.15
     Computer
    0.13
    Computer
    0.12
    çĶµèĦij
    0.11
     COMPUTER
    0.11
     Computers
    0.11
    puter
    0.10
     poÄįÃŃta
    0.10
    Activations Density 0.167%

    No Known Activations