© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76902
    Prev
    Next
    INDEX
    Explanations

    references to substances and financial terms

    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
    getDisplay
    -0.07
     diren
    -0.07
    ï½¥
    -0.07
     !:
    -0.07
    ÙĬدا
    -0.07
    ighet
    -0.07
    lý
    -0.07
    conde
    -0.07
    ienia
    -0.07
     hton
    -0.07
    POSITIVE LOGITS
    ählen
    0.07
    ullen
    0.06
    aga
    0.06
     Accord
    0.06
    agini
    0.06
    kker
    0.05
    /vnd
    0.05
    Tambah
    0.05
    ģn
    0.05
    'S
    0.05
    Activations Density 0.001%

    No Known Activations