© 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. 126640
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to battery performance and capacity in smartphones

    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
    bung
    -0.07
    EIF
    -0.07
    estro
    -0.07
     khảo
    -0.07
    à¹Ĩ
    -0.07
     Bilg
    -0.06
    574
    -0.06
    igm
    -0.06
     prostituer
    -0.06
    dag
    -0.06
    POSITIVE LOGITS
     Li
    0.09
     charge
    0.08
     power
    0.08
     lithium
    0.08
     charging
    0.07
     batteries
    0.07
     recharge
    0.07
     battery
    0.07
     size
    0.07
     Charging
    0.07
    Activations Density 0.004%

    No Known Activations