© 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. 59749
    Prev
    Next
    INDEX
    Explanations

    specific code structure elements in programming

    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
     CAB
    -0.06
    icks
    -0.06
    ink
    -0.06
     Brain
    -0.06
    ets
    -0.06
     lie
    -0.06
    280
    -0.06
    inker
    -0.06
    awa
    -0.05
     intellectual
    -0.05
    POSITIVE LOGITS
     serialVersionUID
    0.10
    kö
    0.08
    ãĥ¼ãĥĨ
    0.07
    adiens
    0.07
    ä¸ļ
    0.07
    ctype
    0.07
    imity
    0.07
    teÅŁ
    0.07
    ģn
    0.07
    :init
    0.06
    Activations Density 0.000%

    No Known Activations