© 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. 124720
    Prev
    Next
    INDEX
    Explanations

    terms related to merchandise and promotional items

    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
    orris
    -0.07
    nings
    -0.07
    ihar
    -0.07
    ÅĽ
    -0.07
    er
    -0.07
    наÑĢ
    -0.06
    bies
    -0.06
    hood
    -0.06
     Zucker
    -0.06
    ners
    -0.06
    POSITIVE LOGITS
    andise
    0.11
    åĵģ
    0.08
     Madness
    0.07
    midt
    0.07
    adow
    0.07
    indle
    0.07
    amburger
    0.07
    ÄŁim
    0.07
    vous
    0.07
    ุม
    0.07
    Activations Density 0.003%

    No Known Activations