© 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. 31035
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal offenses and abuses

    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
    .semantic
    -0.07
    ndata
    -0.06
    coli
    -0.06
    IRS
    -0.06
    丸
    -0.06
    ansi
    -0.06
    ully
    -0.06
    otch
    -0.06
    sect
    -0.06
     notwithstanding
    -0.06
    POSITIVE LOGITS
    èĪ¬
    0.07
    ĩ
    0.07
    ior
    0.07
    оÑĢалÑĮ
    0.06
    Lifetime
    0.06
    .mapbox
    0.06
     Scheduled
    0.06
    anning
    0.06
    VICES
    0.06
     Oval
    0.06
    Activations Density 0.006%

    No Known Activations