© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 78062
    Prev
    Next
    INDEX
    Explanations

    terms related to grocery stores and shopping

    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
    quin
    -0.07
     cont
    -0.06
    var
    -0.06
    ater
    -0.06
    ese
    -0.06
     “
    -0.05
     factorial
    -0.05
     ge
    -0.05
     Secret
    -0.05
     cr
    -0.05
    POSITIVE LOGITS
    tainment
    0.11
    oppins
    0.09
    Sharper
    0.07
    ober
    0.07
    oard
    0.07
     Giants
    0.07
    خاÙĨÙĩ
    0.07
     Giant
    0.07
     DISCLAIM
    0.07
    ìľ¡
    0.07
    Activations Density 0.003%

    No Known Activations