© 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. 94374
    Prev
    Next
    INDEX
    Explanations

    elements related to video games and their narratives

    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
     drill
    -0.07
     Stadium
    -0.06
     Oman
    -0.06
     exp
    -0.06
    -0.06
    IELD
    -0.06
     Drill
    -0.06
     clr
    -0.06
     ext
    -0.05
     Fury
    -0.05
    POSITIVE LOGITS
    ìĸ´ëĤĺ
    0.07
    =$('#
    0.07
    sob
    0.07
    ptype
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    isode
    0.07
    (utf
    0.07
    _java
    0.07
    endl
    0.07
    sap
    0.07
    Activations Density 0.003%

    No Known Activations