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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96066
    Prev
    Next
    INDEX
    Explanations

    references to traffic signals and road safety

    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
    _SECURITY
    -0.07
    à¥Ģण
    -0.06
    aeda
    -0.06
    WithType
    -0.06
    caled
    -0.06
    metro
    -0.06
    _CSR
    -0.06
    illo
    -0.06
    åģ
    -0.06
    ät
    -0.06
    POSITIVE LOGITS
    onnen
    0.07
    /loose
    0.06
    REL
    0.06
     lett
    0.06
    storeId
    0.06
    éŃĤ
    0.06
    ãĥ³ãĥĪ
    0.05
    YL
    0.05
    emek
    0.05
    .Optional
    0.05
    Activations Density 0.004%

    No Known Activations