© 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. 95297
    Prev
    Next
    INDEX
    Explanations

    numerical details related to financial 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
    ÐĦ
    -0.07
    ichten
    -0.07
    issor
    -0.06
    ould
    -0.06
    _reporting
    -0.06
    ubern
    -0.06
    plex
    -0.06
    ember
    -0.06
     поба
    -0.06
    creativecommons
    -0.06
    POSITIVE LOGITS
    髪
    0.07
    ocs
    0.07
     Faction
    0.06
    Cab
    0.06
    è°±
    0.06
    otron
    0.06
    ÙĪد
    0.06
    hair
    0.06
    aira
    0.06
     èĮ
    0.06
    Activations Density 0.001%

    No Known Activations