© 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. 30490
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to various structures and events

    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
    anders
    -0.07
    dera
    -0.07
    ARING
    -0.07
    ấu
    -0.06
    .jetbrains
    -0.06
    ersist
    -0.06
    آ
    -0.06
    istr
    -0.06
    illions
    -0.06
    isy
    -0.06
    POSITIVE LOGITS
    à¹ģรà¸ģ
    0.09
    leases
    0.07
    обов
    0.07
    丸
    0.07
    ãģĨãģ¡
    0.06
    compressed
    0.06
    conds
    0.06
     nutshell
    0.06
     gul
    0.06
    BASH
    0.06
    Activations Density 0.065%

    No Known Activations