© 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. 85773
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person perspective in narrative contexts

    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
    isson
    -0.06
     TestUtils
    -0.06
    resh
    -0.06
    ounty
    -0.06
    Ñĥка
    -0.06
    ittest
    -0.06
    eks
    -0.06
     Harding
    -0.06
     -*-č↵
    -0.06
    ĵ¨
    -0.06
    POSITIVE LOGITS
     blank
    0.07
     temp
    0.06
     net
    0.06
     workout
    0.06
    clamp
    0.06
     bid
    0.05
     Bid
    0.05
    nici
    0.05
    709
    0.05
    ig
    0.05
    Activations Density 0.027%

    No Known Activations