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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73284
    Prev
    Next
    INDEX
    Explanations

    instances of the word "No"

    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
    ale
    -0.07
    alex
    -0.07
    idd
    -0.06
    ter
    -0.06
    at
    -0.06
    ulk
    -0.06
    ksam
    -0.06
    quent
    -0.06
    volent
    -0.06
    ynch
    -0.06
    POSITIVE LOGITS
    malink
    0.10
    abase
    0.07
    TargetException
    0.07
    .Lang
    0.07
     comment
    0.06
    .DataAccess
    0.06
    ABEL
    0.06
     TMPro
    0.06
    ises
    0.06
    째
    0.06
    Activations Density 0.003%

    No Known Activations