© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78256
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and related personal pronouns in various contexts

    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
    .uf
    -0.06
    probably
    -0.06
    /UIKit
    -0.06
    igua
    -0.06
    ograd
    -0.06
    åĬ¡
    -0.06
     probably
    -0.06
    etsk
    -0.06
     ive
    -0.06
     Ive
    -0.05
    POSITIVE LOGITS
     ìĭ¶
    0.07
     your
    0.07
    fy
    0.07
     ÙħÙĤد
    0.07
    ëĵł
    0.07
     yourself
    0.07
     algun
    0.07
     tomorrow
    0.07
    ìŀ¡
    0.07
    rames
    0.07
    Activations Density 0.030%

    No Known Activations