© 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. 78766
    Prev
    Next
    INDEX
    Explanations

    paths or references related to file handling and system directories

    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
     çī©
    -0.06
     ang
    -0.06
    inkel
    -0.06
     Alley
    -0.05
    umer
    -0.05
     advance
    -0.05
    uder
    -0.05
     intro
    -0.05
    coder
    -0.05
     re
    -0.05
    POSITIVE LOGITS
    sep
    0.08
    оÑıн
    0.08
    opi
    0.08
    /filepath
    0.08
    hled
    0.08
    stoup
    0.08
    amba
    0.08
    joining
    0.07
    xbc
    0.07
    heten
    0.07
    Activations Density 0.003%

    No Known Activations