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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95608
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'Y' and its phonetic representations

    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
    ister
    -0.09
    incinn
    -0.08
    åĩĨ
    -0.08
    ino
    -0.08
    omer
    -0.07
    ucci
    -0.07
    lover
    -0.07
    ómo
    -0.07
    ila
    -0.07
    chet
    -0.07
    POSITIVE LOGITS
    ois
    0.08
    GLE
    0.08
    uxtap
    0.08
    ephy
    0.08
     nhiên
    0.07
    ields
    0.07
    osemite
    0.07
    racuse
    0.07
    igsaw
    0.07
    esterday
    0.07
    Activations Density 0.221%

    No Known Activations