© 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 EvalsExportsAPI 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. 60973
    Prev
    Next
    INDEX
    Explanations

    phrases related to the terms and conditions of product orders

    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
    illis
    -0.06
    erea
    -0.06
    aset
    -0.06
    792
    -0.06
    aland
    -0.06
    ajas
    -0.06
     sug
    -0.06
    aska
    -0.06
    uminium
    -0.06
    son
    -0.05
    POSITIVE LOGITS
     klu
    0.09
     knull
    0.07
    аниÑĨ
    0.07
    ARSER
    0.07
    _ordered
    0.06
    oping
    0.06
    æ¥
    0.06
    Bindings
    0.06
    owitz
    0.06
    'order
    0.06
    Activations Density 0.008%

    No Known Activations