© 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. 15-LLAMASCOPE-RES-131K
    11. 88439
    Prev
    Next
    INDEX
    Explanations

    terms related to jewelry, specifically earrings and necklaces

    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
    ä¿Ĭ
    -0.08
    ãĥ³ãĤ¯
    -0.07
    aná
    -0.07
    istik
    -0.07
     Güven
    -0.07
     ÙĪر
    -0.07
    sheets
    -0.07
    phem
    -0.07
    µ¬
    -0.06
    kontakte
    -0.06
    POSITIVE LOGITS
    ifer
    0.06
    -sized
    0.06
    SqlServer
    0.06
    ectomy
    0.06
     pend
    0.05
     earrings
    0.05
    .setDefault
    0.05
    eb
    0.05
    åŃĶ
    0.05
    ģµ
    0.05
    Activations Density 0.007%

    No Known Activations