© 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. 129437
    Prev
    Next
    INDEX
    Explanations

    references to maps and their associated visual or interactive elements

    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
    θμ
    -0.07
    ohana
    -0.07
     Geometry
    -0.07
    анÑģ
    -0.06
    inery
    -0.06
    gars
    -0.06
    ustum
    -0.06
    ÑĢеÑģÑģ
    -0.06
    Protect
    -0.06
     åł
    -0.06
    POSITIVE LOGITS
     Map
    0.08
    map
    0.07
     map
    0.07
     Maps
    0.07
    Map
    0.07
    084
    0.07
    -map
    0.07
     maps
    0.06
    ovic
    0.06
    maps
    0.06
    Activations Density 0.002%

    No Known Activations