© 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. 40359
    Prev
    Next
    INDEX
    Explanations

    terms related to reciprocal relationships or opposing dynamics

    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
    relude
    -0.06
    umo
    -0.06
    illet
    -0.06
    rif
    -0.06
    olt
    -0.06
    esson
    -0.05
    lok
    -0.05
    eln
    -0.05
     gest
    -0.05
    /doc
    -0.05
    POSITIVE LOGITS
     versa
    0.14
     vice
    0.08
    forth
    0.08
    vice
    0.07
    ç©
    0.07
    atab
    0.07
    976
    0.07
     alike
    0.07
    aan
    0.07
    ogany
    0.07
    Activations Density 0.002%

    No Known Activations