© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4565
    Prev
    Next
    INDEX
    Explanations

    phrases related to refunds and return policies

    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
    ypse
    -0.07
    CriticalSection
    -0.07
    ppy
    -0.07
    ymes
    -0.07
    INU
    -0.07
    retty
    -0.07
    (disposing
    -0.07
    воÑĢ
    -0.07
    kelig
    -0.07
    .compiler
    -0.07
    POSITIVE LOGITS
     depending
    0.06
     explanation
    0.06
    ILA
    0.05
     Origin
    0.05
    oker
    0.05
     whichever
    0.05
     explained
    0.05
     Zhou
    0.05
    acement
    0.05
    -begin
    0.05
    Activations Density 0.004%

    No Known Activations