© 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. 128205
    Prev
    Next
    INDEX
    Explanations

    technical references related to data and media formats or links

    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
    ple
    -0.07
     McK
    -0.07
    abeth
    -0.06
    æķ¬
    -0.06
    974
    -0.06
    heimer
    -0.05
    uat
    -0.05
    ît
    -0.05
    nemonic
    -0.05
    uta
    -0.05
    POSITIVE LOGITS
     synd
    0.09
     "-//
    0.08
    (atom
    0.07
     Synd
    0.07
     enclosure
    0.07
    Feed
    0.07
    ÑĤен
    0.07
     Atom
    0.07
     feed
    0.07
     atom
    0.07
    Activations Density 0.002%

    No Known Activations