© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56045
    Prev
    Next
    INDEX
    Explanations

    phrases depicting actions and interactions in various contexts, particularly involving confrontation or conflict

    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
     whole
    -0.07
    ówn
    -0.07
    ÑĩаÑĤ
    -0.07
    posables
    -0.07
     entire
    -0.07
    uida
    -0.07
    ndl
    -0.07
    æģµ
    -0.07
    ableViewController
    -0.07
    azzi
    -0.07
    POSITIVE LOGITS
     unspecified
    0.07
     Ñıк
    0.06
     allegedly
    0.06
     nearby
    0.06
    his
    0.06
    hawk
    0.06
    æľīåħ³
    0.06
     upcoming
    0.06
    æŁIJ
    0.06
    è«ĸ
    0.06
    Activations Density 0.027%

    No Known Activations