© 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. 105522
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical systems and charge interactions

    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
    ynos
    -0.07
    .band
    -0.06
    ulses
    -0.06
    ugen
    -0.06
    GH
    -0.06
    Bars
    -0.06
    .Fat
    -0.06
    ấ
    -0.06
    bands
    -0.06
    íı
    -0.06
    POSITIVE LOGITS
     charge
    0.18
     charges
    0.17
     Charge
    0.17
     Charges
    0.15
    charge
    0.15
     charged
    0.15
    Charge
    0.14
     Charg
    0.14
    charges
    0.14
     charging
    0.13
    Activations Density 0.091%

    No Known Activations