© 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. 39042
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and 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
    ono
    -0.06
    onen
    -0.06
    ãģªãģĬ
    -0.06
    trans
    -0.06
    ö
    -0.06
    adelphia
    -0.06
    alis
    -0.06
    asca
    -0.06
    Forever
    -0.06
    mis
    -0.06
    POSITIVE LOGITS
    CJK
    0.07
    ÑĢозÑĥм
    0.07
     âĹĦ
    0.07
    ourcem
    0.07
    ectl
    0.07
    ariate
    0.07
     directly
    0.07
    /high
    0.07
    vrier
    0.07
    ptive
    0.06
    Activations Density 0.010%

    No Known Activations