© 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. 94521
    Prev
    Next
    INDEX
    Explanations

    information about taxation and financial administration related to goods and services

    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
    berger
    -0.06
     dom
    -0.06
     mamma
    -0.06
     norge
    -0.06
     Tubes
    -0.06
    uppen
    -0.06
     induction
    -0.06
     lo
    -0.06
    AMB
    -0.06
    åįļ
    -0.05
    POSITIVE LOGITS
    StateException
    0.07
    archical
    0.07
    ReuseIdentifier
    0.07
    efeller
    0.07
    efe
    0.06
    çļĦæīĭ
    0.06
    eper
    0.06
    arse
    0.06
    edImage
    0.06
    _OVERRIDE
    0.06
    Activations Density 0.027%

    No Known Activations