© 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. 106944
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" and related ordinal terms

    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
    .records
    -0.07
    .codes
    -0.07
    ónico
    -0.07
    iteli
    -0.07
    etooth
    -0.07
    оÑĢе
    -0.06
    oftware
    -0.06
    okedex
    -0.06
    addin
    -0.06
    .LayoutStyle
    -0.06
    POSITIVE LOGITS
     few
    0.07
    359
    0.07
     girlfriends
    0.06
    airo
    0.06
    152
    0.06
    ym
    0.06
    ippi
    0.06
    (s
    0.06
     Nimbus
    0.06
    irs
    0.06
    Activations Density 0.019%

    No Known Activations