© 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. 127455
    Prev
    Next
    INDEX
    Explanations

    key figures and events related to organizational changes and nominations

    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
     eskort
    -0.08
    ÙģØ´
    -0.08
    ableViewController
    -0.08
    geber
    -0.08
    SpaceItem
    -0.08
    заб
    -0.07
    ìĤ
    -0.07
     pope
    -0.07
    NavController
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     previously
    0.07
     existing
    0.07
     Emergency
    0.07
     emergency
    0.07
    ãĥĥ
    0.07
     familiar
    0.06
     already
    0.06
     internal
    0.06
    0.05
     from
    0.05
    Activations Density 0.033%

    No Known Activations