© 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. 94433
    Prev
    Next
    INDEX
    Explanations

    words that describe favorable conditions or attributes

    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
    ismet
    -0.08
    rored
    -0.07
    izr
    -0.07
    ATAB
    -0.07
    еÑĤÑĥ
    -0.07
    eward
    -0.07
    orang
    -0.07
    ÑĪев
    -0.07
    ÑĢек
    -0.07
    830
    -0.07
    POSITIVE LOGITS
     choice
    0.11
     fit
    0.09
    choice
    0.09
     option
    0.08
     choices
    0.07
    Choice
    0.07
    Reload
    0.07
     Choice
    0.07
     candidate
    0.07
     way
    0.07
    Activations Density 0.029%

    No Known Activations