© 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. 16636
    Prev
    Next
    INDEX
    Explanations

    historical figures and their academic achievements or positions

    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
    subcategory
    -0.07
    ogn
    -0.07
    ourg
    -0.06
    PCA
    -0.06
    uling
    -0.06
    pch
    -0.06
    ourcing
    -0.06
    categorie
    -0.06
    лÑİ
    -0.06
    ngo
    -0.06
    POSITIVE LOGITS
     research
    0.10
    research
    0.09
     publications
    0.08
     Research
    0.07
    èijĹ
    0.07
    çłĶ究
    0.07
     nghiên
    0.07
     publication
    0.07
    nos
    0.06
    196
    0.06
    Activations Density 0.025%

    No Known Activations