© 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. 74943
    Prev
    Next
    INDEX
    Explanations

    terms related to government actions and their impacts

    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
    ĨĴ
    -0.07
    engl
    -0.07
    nech
    -0.07
    llu
    -0.07
    pect
    -0.07
    chie
    -0.07
    벨
    -0.07
    ahren
    -0.06
    riting
    -0.06
    ICO
    -0.06
    POSITIVE LOGITS
    izes
    0.07
     FindObjectOfType
    0.07
    atik
    0.07
    orry
    0.06
    decorators
    0.06
    IRA
    0.06
     Bun
    0.06
    IZES
    0.06
    AtPath
    0.06
     regarding
    0.06
    Activations Density 0.098%

    No Known Activations