© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    JavaScript code structures and syntax elements

    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
    -Cs
    -0.07
    vale
    -0.06
    andas
    -0.06
    ÑĦа
    -0.06
    arkin
    -0.06
    anja
    -0.06
    aran
    -0.06
    *****/↵
    -0.06
    elan
    -0.06
     Carlson
    -0.06
    POSITIVE LOGITS
    abcdefgh
    0.07
    Ø®ÛĮ
    0.07
     bul
    0.06
     Bis
    0.06
    gc
    0.06
     bis
    0.06
    Gravity
    0.06
     Ñĸмп
    0.06
    gan
    0.06
    abcdefghijkl
    0.06
    Activations Density 0.002%

    No Known Activations