© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    phrases about taking initiative or increasing responsibility

    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
    ego
    -0.07
    è§Ī
    -0.06
    ikel
    -0.06
    alem
    -0.06
    kh
    -0.06
    quette
    -0.06
    ammer
    -0.06
    ÙĬدÙĬ
    -0.06
    eniable
    -0.06
    Ing
    -0.06
    POSITIVE LOGITS
     ante
    0.08
    Unnamed
    0.07
     Wich
    0.07
    ToDate
    0.07
    :\/\/
    0.06
    ovit
    0.06
     Paging
    0.06
    ozor
    0.06
    725
    0.06
    ูà¸ģ
    0.06
    Activations Density 0.002%

    No Known Activations