© 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. 17-LLAMASCOPE-RES-131K
    11. 119517
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or regulatory compliance

    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
    ogan
    -0.08
    regor
    -0.07
    éº
    -0.07
    iamo
    -0.07
    neh
    -0.07
    ifen
    -0.06
    359
    -0.06
    ναν
    -0.06
    esz
    -0.06
     geh
    -0.06
    POSITIVE LOGITS
    ped
    0.07
    º«
    0.06
    xca
    0.06
    istrovstvÃŃ
    0.06
    ancellationToken
    0.06
    ancer
    0.06
     XCT
    0.06
    pel
    0.06
    ongs
    0.06
    PAGE
    0.06
    Activations Density 0.001%

    No Known Activations