© 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. 57476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or decisions made by individuals or groups

    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
     nicht
    -0.11
     không
    -0.11
    ä¸įæĺ¯
    -0.11
     not
    -0.11
     não
    -0.10
    ä¸įä¼ļ
    -0.10
     не
    -0.10
     cannot
    -0.10
     tidak
    -0.10
    ä¸įèĥ½
    -0.10
    POSITIVE LOGITS
     instead
    0.14
    Instead
    0.14
     Instead
    0.13
    instead
    0.13
     merely
    0.10
     naopak
    0.08
     simply
    0.08
    Rather
    0.07
     Rather
    0.07
     lại
    0.06
    Activations Density 0.044%

    No Known Activations