Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78369
    Prev
    Next
    INDEX
    Explanations

    brands or services related to flight and travel

    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
    aterno
    -0.08
    ë´ī
    -0.08
    ÑĤеÑĢи
    -0.07
    ãĥĪãĥª
    -0.07
     AsyncStorage
    -0.07
     пиÑĤ
    -0.07
    ÑģÑĤÑĢой
    -0.07
    ItemAt
    -0.07
    ework
    -0.07
    екÑĤи
    -0.07
    POSITIVE LOGITS
    ýn
    0.07
     Peel
    0.07
    ár
    0.07
    pez
    0.06
    han
    0.06
    Äįi
    0.06
    lemen
    0.05
    Łèĥ½
    0.05
    æ
    0.05
    -remove
    0.05
    Activations Density 0.001%

    No Known Activations