© 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. 17-LLAMASCOPE-RES-131K
    11. 84976
    Prev
    Next
    INDEX
    Explanations

    specifications related to display features of devices

    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
     Mister
    -0.06
    abel
    -0.06
    ä¸ĺ
    -0.06
    зв
    -0.06
     ing
    -0.05
     probing
    -0.05
     pace
    -0.05
    .sax
    -0.05
     ku
    -0.05
     hem
    -0.05
    POSITIVE LOGITS
     screen
    0.10
    screen
    0.09
    elik
    0.09
    -screen
    0.09
    .screen
    0.07
     Dün
    0.07
     wides
    0.07
    \views
    0.07
    ytt
    0.07
    ÙĨدگÛĮ
    0.07
    Activations Density 0.011%

    No Known Activations