© 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. 54161
    Prev
    Next
    INDEX
    Explanations

    monetary values and associated numerical data

    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
    ulty
    -0.08
    ÃŃk
    -0.07
    abd
    -0.07
    arp
    -0.06
     unprecedented
    -0.06
    kart
    -0.06
    oe
    -0.06
    oload
    -0.06
    antz
    -0.06
    ARP
    -0.06
    POSITIVE LOGITS
    stan
    0.07
    že
    0.07
     Haram
    0.06
    ráž
    0.06
    .capacity
    0.06
    ÏĦÏī
    0.06
     Hanson
    0.06
    /***/
    0.06
    ÃĹ↵↵
    0.06
     legalized
    0.06
    Activations Density 0.008%

    No Known Activations