© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62434
    Prev
    Next
    INDEX
    Explanations

    processes related to financial reinvestment and issuing stock

    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
     escorte
    -0.07
    èm
    -0.07
    å±¥
    -0.07
    ãĤŃãĥ¥
    -0.07
    atron
    -0.07
     gord
    -0.07
    лаÑģÑĤи
    -0.06
    otton
    -0.06
     Entire
    -0.06
    acak
    -0.06
    POSITIVE LOGITS
    ocker
    0.07
    orge
    0.06
     pods
    0.06
     Pod
    0.05
    gmail
    0.05
     XYZ
    0.05
     obvious
    0.05
     CURL
    0.05
    firm
    0.05
     POD
    0.05
    Activations Density 0.000%

    No Known Activations