© 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. 15-LLAMASCOPE-RES-131K
    11. 776
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases indicating potential actions or obligations

    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
    witter
    -0.07
    ucus
    -0.06
    ëĿ¼ìĿ¸
    -0.06
     ìĪĺê°Ģ
    -0.06
    :{č↵
    -0.06
    innitus
    -0.06
    à¸ķà¸Ļ
    -0.06
    리그
    -0.06
    menin
    -0.06
    اشت
    -0.06
    POSITIVE LOGITS
     results
    0.07
    AKE
    0.07
     resulted
    0.06
    epad
    0.06
     allowing
    0.06
     result
    0.06
    ãĥ¥ãĥ¼
    0.06
    оÑıн
    0.06
    awl
    0.06
    FileSync
    0.06
    Activations Density 0.145%

    No Known Activations