Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11535
    Prev
    Next
    INDEX
    Explanations

    references to geographic or administrative features and terms

    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
    Wire
    -0.07
    asje
    -0.07
     Tham
    -0.07
     rast
    -0.06
    Asia
    -0.06
    è¯ģ
    -0.06
    але
    -0.06
    λοÏħ
    -0.06
    mamak
    -0.06
     OnPropertyChanged
    -0.06
    POSITIVE LOGITS
     prefect
    0.15
     Pref
    0.14
     county
    0.13
     County
    0.13
    County
    0.12
     counties
    0.12
    Pref
    0.12
     Counties
    0.11
    pref
    0.11
    county
    0.10
    Activations Density 0.004%

    No Known Activations