© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108760
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sneaker releases and their features

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     nackte
    -0.09
    ERA
    -0.07
    ahun
    -0.07
    ityEngine
    -0.07
    amaha
    -0.07
    ifetime
    -0.06
     ERA
    -0.06
    itched
    -0.06
     thunk
    -0.06
    cente
    -0.06
    POSITIVE LOGITS
    =<?=
    0.07
    /topic
    0.06
    aks
    0.06
     color
    0.06
    .chapter
    0.06
    ota
    0.06
    .color
    0.06
    idor
    0.06
     oto
    0.06
     emploi
    0.06
    Activations Density 0.028%

    No Known Activations