© 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. 57514
    Prev
    Next
    INDEX
    Explanations

    phrases that express encouragement or appreciation for ongoing efforts

    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
    iaux
    -0.07
    æĨ
    -0.07
    ær
    -0.07
    ekten
    -0.07
    udo
    -0.07
    hip
    -0.06
    PRI
    -0.06
    och
    -0.06
    ftware
    -0.06
    ador
    -0.06
    POSITIVE LOGITS
     momentum
    0.09
     pace
    0.09
    Å¡lo
    0.07
     trend
    0.07
    ToProps
    0.07
    peg
    0.06
    ãĥĥãĤ·ãĥ¥
    0.06
     tempo
    0.06
    aq
    0.06
     tradition
    0.06
    Activations Density 0.004%

    No Known Activations