© 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. 92215
    Prev
    Next
    INDEX
    Explanations

    phrases related to modifications and commands in code or procedural contexts

    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
    ÃŃrk
    -0.08
    ccione
    -0.07
    ceae
    -0.07
    exampleInput
    -0.07
    aterno
    -0.07
    afen
    -0.06
    нав
    -0.06
    InChildren
    -0.06
     Huff
    -0.06
    خرÛĮد
    -0.06
    POSITIVE LOGITS
    POOL
    0.06
    ÏĢά
    0.06
    :[
    0.06
    assin
    0.06
    ï¸
    0.06
     Katz
    0.06
    oha
    0.05
    utor
    0.05
     Vie
    0.05
    UEL
    0.05
    Activations Density 0.072%

    No Known Activations