© 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. 9-LLAMASCOPE-RES-131K
    11. 97994
    Prev
    Next
    INDEX
    Explanations

    references to currency and financial terminology

    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
     pros
    -0.06
     turn
    -0.06
    oka
    -0.06
    essor
    -0.06
     l
    -0.06
     cough
    -0.05
     flick
    -0.05
    oud
    -0.05
    rov
    -0.05
     pre
    -0.05
    POSITIVE LOGITS
    upil
    0.07
    taj
    0.07
     Lawson
    0.07
     تخ
    0.07
    -medium
    0.06
     letto
    0.06
    Äįer
    0.06
     bearer
    0.06
    ingleton
    0.06
     خط
    0.06
    Activations Density 0.012%

    No Known Activations