© 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. 76552
    Prev
    Next
    INDEX
    Explanations

    concepts related to the scheduling and execution of tests in programming or software development

    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
    _sizes
    -0.07
     nors
    -0.07
    jni
    -0.07
    软
    -0.06
    åĽ
    -0.06
     soft
    -0.06
    ZA
    -0.06
     Tele
    -0.06
    _soft
    -0.06
    _RET
    -0.06
    POSITIVE LOGITS
     independent
    0.07
    bast
    0.07
     Independent
    0.07
    á»ķ
    0.07
    Independent
    0.07
    -independent
    0.06
     independence
    0.06
     independ
    0.06
     independents
    0.06
     Hammer
    0.06
    Activations Density 0.012%

    No Known Activations