© 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. 5-LLAMASCOPE-RES-131K
    11. 126953
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and actions

    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
    ello
    -0.06
    fty
    -0.06
    adows
    -0.06
    FromClass
    -0.06
     vit
    -0.06
    ibir
    -0.06
    qus
    -0.06
     Tat
    -0.06
     Slee
    -0.06
    ucid
    -0.06
    POSITIVE LOGITS
    inery
    0.07
    ÅŁa
    0.07
    PAIR
    0.07
    alnız
    0.06
    enton
    0.06
    鹿
    0.06
     geçir
    0.06
     consenting
    0.06
    int
    0.06
     pew
    0.06
    Activations Density 0.027%

    No Known Activations