© 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. 105763
    Prev
    Next
    INDEX
    Explanations

    expressions related to demonstrating capability or potential

    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
    aled
    -0.07
    arna
    -0.07
    ÑģоÑĤ
    -0.07
    immel
    -0.07
    ruba
    -0.07
    ãģķãģ¾
    -0.07
    nex
    -0.06
     irony
    -0.06
    Friendly
    -0.06
    анÑģи
    -0.06
    POSITIVE LOGITS
     prove
    0.10
     proves
    0.07
     proof
    0.07
    è¯ģæĺİ
    0.07
    abis
    0.07
     capabilities
    0.07
    proof
    0.07
     doub
    0.06
     abilities
    0.06
     proven
    0.06
    Activations Density 0.017%

    No Known Activations