© 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. 17-LLAMASCOPE-RES-131K
    11. 59895
    Prev
    Next
    INDEX
    Explanations

    details related to tax calculations and rebate amounts

    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
    ehler
    -0.06
    abeth
    -0.05
    hausen
    -0.05
    awan
    -0.05
    .
    -0.05
    ugins
    -0.05
    ourke
    -0.05
    :
    -0.05
     via
    -0.05
    PPER
    -0.05
    POSITIVE LOGITS
    жд
    0.08
    aru
    0.07
    _specs
    0.07
    jedn
    0.07
    ä¸ī级
    0.07
    WRAPPER
    0.07
    .Spring
    0.07
    обов
    0.07
    عاد
    0.07
    _THAT
    0.06
    Activations Density 0.007%

    No Known Activations