© 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. 73833
    Prev
    Next
    INDEX
    Explanations

    phrases related to consumer savings and financial products

    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
    SED
    -0.07
    à¥įद
    -0.07
    coles
    -0.06
    под
    -0.06
    Reflection
    -0.06
     Reflection
    -0.06
    fifo
    -0.06
    availability
    -0.06
     grues
    -0.06
    žel
    -0.06
    POSITIVE LOGITS
    /free
    0.07
    832
    0.07
    undle
    0.07
    icht
    0.07
    lab
    0.06
    inue
    0.06
    orney
    0.06
    اÛĮت
    0.06
    å¡
    0.06
    oft
    0.06
    Activations Density 0.008%

    No Known Activations