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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3467
    Prev
    Next
    INDEX
    Explanations

    financial information related to individuals, particularly income sources and earnings

    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
    abin
    -0.07
    nech
    -0.07
    erce
    -0.07
    iyel
    -0.07
    ntl
    -0.07
    anza
    -0.06
    ophage
    -0.06
    ictures
    -0.06
    _CONV
    -0.06
     Orr
    -0.06
    POSITIVE LOGITS
     income
    0.07
     earnings
    0.07
     Inn
    0.06
     Lesser
    0.06
     kiếm
    0.06
     innate
    0.06
     salary
    0.06
     inn
    0.06
    μ
    0.06
     доÑħод
    0.05
    Activations Density 0.003%

    No Known Activations