© 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. 28402
    Prev
    Next
    INDEX
    Explanations

    negations and quantity references in relation to the distribution of resources or substances

    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
     Julio
    -0.06
    ahn
    -0.06
     santa
    -0.06
    loff
    -0.06
    937
    -0.06
     prox
    -0.06
     lifestyle
    -0.06
     attempting
    -0.05
    joy
    -0.05
    زÙĦ
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤ¬
    0.08
    andbox
    0.07
    หย
    0.07
    oji
    0.07
    伦
    0.07
     Circular
    0.07
    меÑĩ
    0.07
    abox
    0.07
    quito
    0.07
    interopRequire
    0.07
    Activations Density 0.000%

    No Known Activations