© 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. 106475
    Prev
    Next
    INDEX
    Explanations

    statistical data related to demographics

    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
    exampleModal
    -0.07
    wright
    -0.07
    PlainText
    -0.07
    iÄĻ
    -0.07
    andaÅŁ
    -0.06
    pto
    -0.06
    bler
    -0.06
    QUOTE
    -0.06
    achts
    -0.06
    jak
    -0.05
    POSITIVE LOGITS
    Ïģαν
    0.07
    ickers
    0.07
     Murdoch
    0.07
    rib
    0.07
    nger
    0.06
    iero
    0.06
    TeV
    0.06
     dây
    0.06
    chan
    0.06
    itivity
    0.06
    Activations Density 0.002%

    No Known Activations