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. 56138
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial investments

    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
    owitz
    -0.06
     Ded
    -0.06
    ŀ
    -0.06
    ley
    -0.05
    barang
    -0.05
    ucer
    -0.05
    isi
    -0.05
     mer
    -0.05
    æ²ĸ
    -0.05
    .Operator
    -0.05
    POSITIVE LOGITS
     estimated
    0.14
     $
    0.13
     worth
    0.12
     cost
    0.12
    cost
    0.12
    ä»·å̼
    0.12
    estimated
    0.11
    Estimated
    0.11
     costs
    0.11
    ">$
    0.11
    Activations Density 0.217%

    No Known Activations