© 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. 86672
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or financial advice

    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
     Certificate
    -0.06
    /Users
    -0.06
     Cipher
    -0.06
    icher
    -0.06
    âĢ¦"↵↵
    -0.06
     wholesale
    -0.06
    arga
    -0.06
     wParam
    -0.06
    /****************************************************************************↵
    -0.06
     Meer
    -0.06
    POSITIVE LOGITS
     claim
    0.07
    mite
    0.06
    jad
    0.06
    backs
    0.06
     UIF
    0.06
    amac
    0.06
    vida
    0.06
     prefect
    0.06
    WN
    0.06
    portlet
    0.06
    Activations Density 0.002%

    No Known Activations