© 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 EvalsExportsinterp-engineNEWAPI 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. 73389
    Prev
    Next
    INDEX
    Explanations

    concepts related to dualities or comparisons in societal contexts

    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
    rimp
    -0.06
     Hlav
    -0.06
    antis
    -0.06
    malink
    -0.06
     Lair
    -0.06
    istence
    -0.06
    wake
    -0.06
    éĿĪ
    -0.06
    âĢ¡
    -0.06
    opper
    -0.06
    POSITIVE LOGITS
    896
    0.07
    ioni
    0.07
    akat
    0.07
     dü
    0.06
    Äįer
    0.06
    uckle
    0.06
    acer
    0.06
    utenberg
    0.06
     depends
    0.06
    Å¡k
    0.06
    Activations Density 0.055%

    No Known Activations