© 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. 89770
    Prev
    Next
    INDEX
    Explanations

    coding-related conditional expressions and control structures

    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
    DialogTitle
    -0.06
    SCO
    -0.06
    ple
    -0.06
     ÑĦаÑĢ
    -0.06
    erner
    -0.06
    /live
    -0.05
    деÑĢж
    -0.05
    066
    -0.05
    sel
    -0.05
    scopes
    -0.05
    POSITIVE LOGITS
    exit
    0.08
     final
    0.08
     finale
    0.08
    entiful
    0.07
     exit
    0.07
    ç»ĵæĿŁ
    0.07
     FINAL
    0.07
     졸
    0.07
    éĢĢåĩº
    0.07
    zp
    0.07
    Activations Density 0.037%

    No Known Activations