© 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. 15-LLAMASCOPE-RES-131K
    6. 61830
    Prev
    Next
    INDEX
    Explanations

    terms related to IP addresses and phone numbers

    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
     Maker
    -0.07
    izi
    -0.07
     Jako
    -0.06
     Ning
    -0.06
    ifax
    -0.06
    oom
    -0.06
    ke
    -0.06
    夫
    -0.06
    /help
    -0.06
    <location
    -0.06
    POSITIVE LOGITS
    precated
    0.07
    ãĥ³ãĥij
    0.07
    edic
    0.07
    åĿĢ
    0.07
    pai
    0.07
    cura
    0.07
    /topics
    0.07
    ç·
    0.07
    :animated
    0.06
    ëĮĢíijľ
    0.06
    Activations Density 0.031%

    No Known Activations