© 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. 95936
    Prev
    Next
    INDEX
    Explanations

    specific food-related ingredients or toppings

    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
    æĿī
    -0.08
    terra
    -0.07
    RequestMethod
    -0.07
    ienda
    -0.07
    ima
    -0.07
    ledon
    -0.07
    anken
    -0.07
    IMA
    -0.07
    lut
    -0.07
    mazon
    -0.07
    POSITIVE LOGITS
    è¾
    0.07
     discrete
    0.06
    rops
    0.06
    é½
    0.06
     toppings
    0.06
    /top
    0.06
     arp
    0.05
     decentral
    0.05
    add
    0.05
    top
    0.05
    Activations Density 0.115%

    No Known Activations