© 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. 5-LLAMASCOPE-RES-131K
    11. 125639
    Prev
    Next
    INDEX
    Explanations

    mathematical structures related to cases or conditional statements

    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
    arel
    -0.07
    avier
    -0.07
    igue
    -0.07
    awan
    -0.06
    hek
    -0.06
     thirsty
    -0.06
    ÑĢаг
    -0.06
    onas
    -0.06
     fountain
    -0.05
    ÑĩеÑĤ
    -0.05
    POSITIVE LOGITS
    zure
    0.06
    Bindable
    0.06
    pace
    0.06
    оÑĢод
    0.06
    flash
    0.06
    iel
    0.06
    archive
    0.06
    leaf
    0.06
    logs
    0.06
    PACE
    0.06
    Activations Density 0.014%

    No Known Activations