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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27090
    Prev
    Next
    INDEX
    Explanations

    references to taxation and employment regulations

    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
    !=(
    -0.07
    agg
    -0.06
     squ
    -0.06
    oidal
    -0.06
    λή
    -0.06
     mole
    -0.06
    é©Ĺ
    -0.06
     tract
    -0.06
    _UNDER
    -0.06
    ABCDEFG
    -0.06
    POSITIVE LOGITS
    åĬ
    0.07
    ham
    0.07
     Employer
    0.06
    figcaption
    0.06
    èĸ
    0.06
    ipers
    0.06
    hma
    0.06
    éĽ
    0.06
    phant
    0.06
    ç´ł
    0.06
    Activations Density 0.001%

    No Known Activations