© 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 EvalsExportsinterp-engineNEWAPI 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. 87803
    Prev
    Next
    INDEX
    Explanations

    mentions of computer science and its relevance to job prospects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text discussing technology careers, computer science education, or technical professional roles.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    $__
    -0.07
    eczy
    -0.07
    ustomed
    -0.07
    ATAB
    -0.07
    èĩªæ²»
    -0.06
    é³´
    -0.06
    ily
    -0.06
    imli
    -0.06
    ảnh
    -0.06
     dur
    -0.06
    POSITIVE LOGITS
     computer
    0.10
     Computer
    0.09
     tech
    0.09
     Technical
    0.09
    computer
    0.09
     technical
    0.09
     Software
    0.09
     Tech
    0.09
     Technology
    0.08
     technological
    0.08
    Activations Density 0.228%

    No Known Activations