© 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. 62500
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to product specifications and branding in industrial contexts

    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
    adin
    -0.06
    ãģĮãģĦ
    -0.06
    hardt
    -0.06
    ëĤĺëĿ¼
    -0.06
    abcdefghijklmnop
    -0.06
    çĽĸ
    -0.06
     wholes
    -0.06
     paralysis
    -0.06
    anton
    -0.06
    ench
    -0.06
    POSITIVE LOGITS
    âĦ¢
    0.10
    TM
    0.10
    ®
    0.09
    ®,
    0.09
    imizer
    0.09
    (TM
    0.08
     Classic
    0.08
    -brand
    0.08
    Plus
    0.07
    ystems
    0.07
    Activations Density 0.035%

    No Known Activations