© 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. 55617
    Prev
    Next
    INDEX
    Explanations

    variable assignments in code

    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
    irm
    -0.06
    structor
    -0.06
    ican
    -0.06
    HING
    -0.06
     getLogger
    -0.06
    Interop
    -0.06
    macen
    -0.06
    975
    -0.06
    pons
    -0.05
    ern
    -0.05
    POSITIVE LOGITS
     null
    0.09
    null
    0.08
    NullOrEmpty
    0.07
    _null
    0.06
    CCR
    0.06
    ostel
    0.06
    	null
    0.06
    ãĤ´ãĥª
    0.06
    aid
    0.06
    aram
    0.06
    Activations Density 0.035%

    No Known Activations