© 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. 85643
    Prev
    Next
    INDEX
    Explanations

    terms related to plus-size clothing and fashion

    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
    itch
    -0.07
     "
    -0.06
    alis
    -0.06
     ...↵
    -0.05
    :
    -0.05
     Total
    -0.05
    alist
    -0.05
    irts
    -0.05
    idge
    -0.05
    osu
    -0.05
    POSITIVE LOGITS
    Tween
    0.08
    اعد
    0.08
    adel
    0.07
    rippling
    0.07
    견
    0.07
    Č↵
    0.07
     doma
    0.07
    ucher
    0.07
    HOLDER
    0.07
    OWNER
    0.07
    Activations Density 0.010%

    No Known Activations