© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119431
    Prev
    Next
    INDEX
    Explanations

    words related to file handling and synchronization 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
    ÂŃn
    -0.07
    sel
    -0.07
    å¿
    -0.06
     LogManager
    -0.06
    iffin
    -0.06
    ariant
    -0.06
    âĹİ
    -0.06
    áng
    -0.06
     %+
    -0.06
    ken
    -0.06
    POSITIVE LOGITS
    flater
    0.06
     nal
    0.06
    214
    0.06
    ame
    0.06
     Fiscal
    0.06
     McGu
    0.06
    .GetText
    0.06
    ered
    0.06
    .DataContext
    0.06
    dos
    0.06
    Activations Density 0.002%

    No Known Activations