© 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. 87081
    Prev
    Next
    INDEX
    Explanations

    CSS class modifiers related to responsive design

    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
    ifen
    -0.06
    oods
    -0.06
    etCode
    -0.06
    ancellable
    -0.06
    ootball
    -0.06
     Moody
    -0.06
    zin
    -0.06
    oggle
    -0.06
    apo
    -0.06
    ioni
    -0.06
    POSITIVE LOGITS
    Å¡ov
    0.07
    <location
    0.06
    ãĥĭãĥĥãĤ¯
    0.06
     JMP
    0.06
    +:
    0.06
     reportedly
    0.06
    HEADER
    0.06
    errer
    0.06
    anz
    0.06
    habi
    0.06
    Activations Density 0.002%

    No Known Activations