© 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. 55409
    Prev
    Next
    INDEX
    Explanations

    references to open mic events and related gatherings

    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
    azon
    -0.07
     getArguments
    -0.07
    ierz
    -0.07
    ارات
    -0.07
    ican
    -0.07
    ÙĬدÙĬ
    -0.06
    Argument
    -0.06
    reen
    -0.06
     symmetry
    -0.06
    _ARGUMENT
    -0.06
    POSITIVE LOGITS
     talent
    0.07
    mae
    0.06
    å¿Ĺ
    0.06
    ηγ
    0.06
     prompt
    0.06
    crawl
    0.06
     fee
    0.06
     formats
    0.06
    formats
    0.06
     genres
    0.06
    Activations Density 0.005%

    No Known Activations