© 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. 82777
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or change in agreements and situations

    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
    onom
    -0.06
    och
    -0.06
    rie
    -0.06
    Chooser
    -0.06
    oren
    -0.05
     brief
    -0.05
     Herm
    -0.05
    roots
    -0.05
     otherwise
    -0.05
    wyn
    -0.05
    POSITIVE LOGITS
    ãģ¾ãģł
    0.11
     still
    0.11
    still
    0.10
     henüz
    0.10
     Still
    0.10
    Still
    0.10
     masih
    0.10
     ÙĩÙĨÙĪز
    0.10
    å°ļ
    0.10
    è¿ĺ
    0.09
    Activations Density 0.025%

    No Known Activations