© 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. 15-LLAMASCOPE-RES-131K
    11. 103454
    Prev
    Next
    INDEX
    Explanations

    instructions related to user account registration processes

    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
    orks
    -0.08
     danmark
    -0.08
     addCriterion
    -0.07
    NetMessage
    -0.07
     پا
    -0.07
    rych
    -0.07
    reib
    -0.07
    UrlParser
    -0.07
    DataExchange
    -0.07
    .trip
    -0.07
    POSITIVE LOGITS
     div
    0.06
     Bett
    0.06
     haz
    0.05
    (required
    0.05
     Gamb
    0.05
    fu
    0.05
     Winn
    0.05
    XC
    0.05
     empty
    0.05
     menstr
    0.05
    Activations Density 0.009%

    No Known Activations