© 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. 15-LLAMASCOPE-RES-131K
    11. 90506
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures 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
     bott
    -0.08
    odos
    -0.07
     bill
    -0.06
     recom
    -0.06
     slack
    -0.06
    æĸ°èģŀ
    -0.06
    _macros
    -0.06
     tam
    -0.06
    mens
    -0.06
    RTL
    -0.06
    POSITIVE LOGITS
    ibli
    0.07
    lator
    0.07
    frey
    0.06
    rian
    0.06
    wei
    0.06
    iggins
    0.06
    ussian
    0.06
    íķĻê³¼
    0.06
    ickets
    0.06
    venth
    0.06
    Activations Density 0.000%

    No Known Activations