© 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. 93669
    Prev
    Next
    INDEX
    Explanations

    instances of the word "please" and related phrases suggesting courteous requests or conditions for response

    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
    olley
    -0.07
     kv
    -0.07
    anity
    -0.07
    erts
    -0.07
    ermann
    -0.06
    anzi
    -0.06
    ochen
    -0.06
     klu
    -0.06
    ¦¬
    -0.06
    etur
    -0.06
    POSITIVE LOGITS
     chances
    0.09
     thì
    0.08
     ÙģÙĤد
    0.07
    then
    0.07
     then
    0.07
     ÙģØ¥ÙĨ
    0.06
    łí
    0.06
     odds
    0.06
     matters
    0.06
    Å¡em
    0.06
    Activations Density 0.009%

    No Known Activations