© 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. 81832
    Prev
    Next
    INDEX
    Explanations

    financial institutions and related monetary transactions

    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
    łí
    -0.07
     Miner
    -0.07
    estre
    -0.06
    èŃľ
    -0.06
    <*
    -0.06
    .scalablytyped
    -0.06
     ÄĮech
    -0.06
    Ñģклад
    -0.06
    FunctionFlags
    -0.06
    /*č↵
    -0.06
    POSITIVE LOGITS
    obot
    0.07
    ag
    0.07
    REP
    0.06
    ÏĦοκ
    0.06
     Commercial
    0.06
    INCREMENT
    0.06
    erton
    0.06
    BOT
    0.06
    960
    0.06
     project
    0.06
    Activations Density 0.005%

    No Known Activations