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. 96215
    Prev
    Next
    INDEX
    Explanations

    references to judicial decisions and their implications

    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
    jang
    -0.07
    otte
    -0.07
    usercontent
    -0.07
    ajaran
    -0.07
    idar
    -0.07
    nech
    -0.07
    ÑĢог
    -0.07
    olean
    -0.06
    ÙĪÙģ
    -0.06
    ItemSelectedListener
    -0.06
    POSITIVE LOGITS
    divid
    0.07
    anko
    0.06
    hell
    0.06
    airs
    0.06
    xC
    0.06
     vista
    0.06
    dik
    0.06
    rial
    0.05
     Lions
    0.05
    mini
    0.05
    Activations Density 0.011%

    No Known Activations