© 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. 27498
    Prev
    Next
    INDEX
    Explanations

    specific programming languages and development frameworks

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

    Prepositions like "in", "with", "using", "on" following verbs like "written", "built", "developed" when describing software, applications, or technical implementations in a programming language or technology.

    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
    .scalablytyped
    -0.09
    arpa
    -0.08
    seau
    -0.08
    ertino
    -0.07
    ordion
    -0.07
    dej
    -0.07
    childs
    -0.07
    asta
    -0.06
    antt
    -0.06
    ãĥ¼ãĤ
    -0.06
    POSITIVE LOGITS
    eny
    0.06
    IMER
    0.06
     Romeo
    0.06
    çĶ²
    0.06
    .Blocks
    0.06
    thon
    0.06
    issen
    0.06
    edit
    0.06
    animate
    0.06
     dib
    0.06
    Activations Density 0.014%

    No Known Activations