© 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. 74532
    Prev
    Next
    INDEX
    Explanations

    references to the United States

    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
    ÑģÑı
    -0.07
    aper
    -0.07
    gether
    -0.07
    istrovstvÃŃ
    -0.07
    il
    -0.07
    645
    -0.06
    mente
    -0.06
    ramework
    -0.06
    anim
    -0.06
    dict
    -0.06
    POSITIVE LOGITS
    (ns
    0.09
     Latina
    0.09
     BirleÅŁik
    0.09
     Samoa
    0.08
    اÙĦÛĮ
    0.08
    /E
    0.08
    -wide
    0.07
    /world
    0.07
    zahl
    0.07
    -Israel
    0.07
    Activations Density 0.016%

    No Known Activations