© 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 EvalsExportsinterp-engineNEWAPI 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. 107741
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a sense of immersion or emotional connection to environments

    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
    æ·¡
    -0.07
    ugin
    -0.07
    ieber
    -0.07
    amet
    -0.07
    ad
    -0.06
    á»iji
    -0.06
    é»ĺ
    -0.06
     OMIT
    -0.06
    rompt
    -0.06
     strr
    -0.06
    POSITIVE LOGITS
    eldo
    0.06
    .Debugger
    0.06
    rabbit
    0.06
     piece
    0.06
     transported
    0.06
    ODY
    0.06
     worlds
    0.06
     Heath
    0.06
     Brady
    0.05
     privat
    0.05
    Activations Density 0.013%

    No Known Activations