© 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. 40398
    Prev
    Next
    INDEX
    Explanations

    references to citizenship and eligibility criteria

    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
    _FAMILY
    -0.07
     spare
    -0.07
    ÅĽnie
    -0.06
    ähr
    -0.06
    ofilm
    -0.06
    363
    -0.06
    altar
    -0.06
    antz
    -0.06
    acam
    -0.06
    adoo
    -0.06
    POSITIVE LOGITS
     ÙħÙĪاط
    0.08
    ãĥ¢ãĥ³
    0.06
    itizen
    0.06
    вад
    0.06
    ÙĦÛĮت
    0.06
    owitz
    0.06
     def
    0.06
    ìĦ¤
    0.06
     Со
    0.06
    STATUS
    0.06
    Activations Density 0.007%

    No Known Activations