© 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. 17-LLAMASCOPE-RES-131K
    11. 28028
    Prev
    Next
    INDEX
    Explanations

    terms related to programming specifications and processes

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

    Terminal output logs between the ">>" markers, often showing error messages, exit codes, execution status, or time elapsed information from various command-line tools like test runners, build systems, and container platforms.

    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
    ler
    -0.06
     county
    -0.06
    undo
    -0.05
    by
    -0.05
    oter
    -0.05
     exper
    -0.05
     Thrones
    -0.05
     ips
    -0.05
    uce
    -0.05
    uzzi
    -0.05
    POSITIVE LOGITS
     NGX
    0.08
    ạ
    0.07
    znik
    0.07
     gian
    0.07
    unik
    0.07
     automát
    0.07
    :Register
    0.07
    chein
    0.07
    skirts
    0.07
    placeholders
    0.07
    Activations Density 0.027%

    No Known Activations