© 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. 84523
    Prev
    Next
    INDEX
    Explanations

    specific mentions of institutions and formal titles in academic and governmental contexts

    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
    á»įng
    -0.06
    Äĥng
    -0.06
    ickness
    -0.06
    elight
    -0.06
    θι
    -0.06
    aternity
    -0.06
    æĢķ
    -0.05
    ibold
    -0.05
    ảnh
    -0.05
     Hers
    -0.05
    POSITIVE LOGITS
     University
    0.09
     United
    0.08
     universe
    0.08
     u
    0.08
     university
    0.08
    *u
    0.08
    _u
    0.08
    uuml
    0.08
    u
    0.07
    UiThread
    0.07
    Activations Density 0.319%

    No Known Activations