Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5595
    Prev
    Next
    INDEX
    Explanations

    titles of movies or references to cinematic works

    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
    ÏĮÏģ
    -0.07
     tas
    -0.07
    kea
    -0.07
    ¯ÃĤ
    -0.07
    mdi
    -0.07
    ãĥ³ãĤ¬
    -0.07
    ëł´
    -0.07
    orda
    -0.06
    nex
    -0.06
    boru
    -0.06
    POSITIVE LOGITS
     Ocean
    0.08
     thieves
    0.08
     cro
    0.08
     con
    0.07
     thief
    0.07
     stealing
    0.07
     rob
    0.07
     master
    0.07
     vault
    0.07
     planning
    0.06
    Activations Density 0.008%

    No Known Activations