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. 126709
    Prev
    Next
    INDEX
    Explanations

    recommendations for food experiences and dining options in Bangkok

    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
    imus
    -0.07
    .scalablytyped
    -0.07
    ÑģилÑĮ
    -0.07
    ÂŃi
    -0.07
     milit
    -0.07
    ocha
    -0.06
    ëĵł
    -0.06
     æŀ
    -0.06
    ê¹Į
    -0.06
    ãĥ³ãĤ°ãĥ«
    -0.06
    POSITIVE LOGITS
     street
    0.08
     restaurants
    0.07
     Mich
    0.07
    qq
    0.07
     Yelp
    0.07
     culture
    0.07
    auth
    0.07
     sokak
    0.07
     Culture
    0.06
    street
    0.06
    Activations Density 0.032%

    No Known Activations