© 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 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. 71604
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax for function definitions in programming contexts

    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
    ipt
    -0.08
    ssue
    -0.07
    ulos
    -0.07
    locks
    -0.06
    heck
    -0.06
    FINE
    -0.06
    çīĩ
    -0.06
     Lease
    -0.06
    phy
    -0.06
    æĿ¯
    -0.06
    POSITIVE LOGITS
     def
    0.09
    avir
    0.07
    aron
    0.06
    é¾į
    0.06
     Russell
    0.06
    oron
    0.06
    ="""
    0.06
    ÏĢή
    0.06
     Stern
    0.06
    anda
    0.06
    Activations Density 0.002%

    No Known Activations