© 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. 120416
    Prev
    Next
    INDEX
    Explanations

    requests for information regarding events or schedules

    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
    öyle
    -0.06
    atura
    -0.06
     noct
    -0.05
     Sat
    -0.05
    åįĪ
    -0.05
     lo
    -0.05
     kin
    -0.05
    dl
    -0.05
    DL
    -0.05
    undle
    -0.05
    POSITIVE LOGITS
     Bilim
    0.07
     jadx
    0.07
    geme
    0.07
     NSStringFromClass
    0.07
     Weekly
    0.07
    ëŁ
    0.07
    oyer
    0.07
    odb
    0.07
    Weekly
    0.07
     æ´»
    0.07
    Activations Density 0.015%

    No Known Activations