© 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. 56755
    Prev
    Next
    INDEX
    Explanations

    specific references to government actions and economic activities

    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
    otech
    -0.08
    .tell
    -0.06
    hei
    -0.06
    ÑĤÑĮ
    -0.06
     też
    -0.06
     Barker
    -0.06
    heim
    -0.06
    teg
    -0.06
     Weiss
    -0.06
    uilt
    -0.06
    POSITIVE LOGITS
    erece
    0.07
    hsi
    0.07
     tonight
    0.07
    ġ
    0.07
    Æ°a
    0.07
    929
    0.07
    ableObject
    0.07
    ignum
    0.07
     ÙĪØ°ÙĦÙĥ
    0.06
     hereby
    0.06
    Activations Density 0.118%

    No Known Activations