© 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. 119201
    Prev
    Next
    INDEX
    Explanations

    programming keywords and structural elements related to directives and classes

    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
    bia
    -0.06
    actal
    -0.06
    ocommerce
    -0.06
    anta
    -0.06
     Cert
    -0.06
     MX
    -0.06
    712
    -0.06
    selectedIndex
    -0.06
    lio
    -0.06
     Constant
    -0.06
    POSITIVE LOGITS
    ãĤ¶
    0.06
     ElementRef
    0.06
     piger
    0.06
    Assembly
    0.06
    lett
    0.06
    TRL
    0.06
    /Area
    0.06
     anmeld
    0.06
     addCriterion
    0.06
     bend
    0.06
    Activations Density 0.000%

    No Known Activations