© 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. 39045
    Prev
    Next
    INDEX
    Explanations

    phrases related to fraudulent activity and legal proceedings

    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
    owie
    -0.06
    abbo
    -0.06
    oppel
    -0.06
    rane
    -0.06
     might
    -0.06
    lant
    -0.06
    hum
    -0.06
     diff
    -0.06
    ãĥ«ãĥĪ
    -0.06
     chances
    -0.06
    POSITIVE LOGITS
    -hide
    0.07
    ứ
    0.06
    âĹİ
    0.06
    daily
    0.06
    atchet
    0.06
    .NewRequest
    0.06
    ëĺIJ
    0.06
     Hide
    0.06
    æį·
    0.06
    bserv
    0.06
    Activations Density 0.001%

    No Known Activations