© 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. 125877
    Prev
    Next
    INDEX
    Explanations

    phrases related to waiting and time management

    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
    AGMA
    -0.07
    ucs
    -0.07
    éĭ
    -0.07
    TOCOL
    -0.07
    bero
    -0.07
    еÑĢÑĤи
    -0.07
    errupted
    -0.06
    ãģ¾ãģļ
    -0.06
    ilece
    -0.06
    abb
    -0.06
    POSITIVE LOGITS
     permanent
    0.09
     later
    0.08
     Permanent
    0.07
     longer
    0.07
     eventual
    0.07
    Permanent
    0.07
    434
    0.07
     eventually
    0.07
     proper
    0.06
    permanent
    0.06
    Activations Density 0.018%

    No Known Activations