© 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. 105316
    Prev
    Next
    INDEX
    Explanations

    references to fictional character development and gameplay mechanics

    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
    vron
    -0.07
    koli
    -0.07
    $MESS
    -0.07
    .experimental
    -0.07
    achel
    -0.07
    -gradient
    -0.07
    lrt
    -0.06
    MemoryWarning
    -0.06
     Knot
    -0.06
    aylight
    -0.06
    POSITIVE LOGITS
     cos
    0.06
     lane
    0.06
    rex
    0.06
     cross
    0.06
     deck
    0.06
     Street
    0.05
     matches
    0.05
     Judgment
    0.05
    estro
    0.05
     court
    0.05
    Activations Density 0.014%

    No Known Activations