© 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 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. 17-LLAMASCOPE-RES-131K
    11. 128939
    Prev
    Next
    INDEX
    Explanations

    concepts related to tax deductions and financial planning

    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
    磨
    -0.07
    aru
    -0.07
    strain
    -0.06
    å±¥
    -0.06
    _OM
    -0.06
     Barg
    -0.06
    cej
    -0.06
    برÛĮ
    -0.06
    ickle
    -0.06
    imson
    -0.06
    POSITIVE LOGITS
     option
    0.07
     Trap
    0.07
     Scenario
    0.06
     options
    0.06
    izzard
    0.06
    EXIT
    0.06
    quential
    0.06
     Leg
    0.06
     asset
    0.06
     planning
    0.06
    Activations Density 0.011%

    No Known Activations