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

    Neuronpedia

    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. 130165
    Prev
    Next
    INDEX
    Explanations

    references to characters and titles in pop culture

    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
     Atlanta
    -0.07
    .builder
    -0.07
     Georgia
    -0.06
     Mandal
    -0.06
    918
    -0.06
     Chicago
    -0.06
     Nashville
    -0.06
    Atlanta
    -0.06
     Bolton
    -0.06
     chicago
    -0.06
    POSITIVE LOGITS
     Hedge
    0.09
     hedge
    0.09
     Bristol
    0.08
    ector
    0.08
     Sonic
    0.08
     hed
    0.08
    ADX
    0.07
     Glouce
    0.07
    Kansas
    0.07
    onic
    0.07
    Activations Density 0.001%

    No Known Activations