© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107326
    Prev
    Next
    INDEX
    Explanations

    terms related to military groups and educational classes

    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
    orget
    -0.07
     Booth
    -0.06
    ooth
    -0.05
    DEL
    -0.05
    ova
    -0.05
    ype
    -0.05
     Wing
    -0.05
    Ħ
    -0.05
     customer
    -0.05
    /angular
    -0.05
    POSITIVE LOGITS
     leader
    0.11
    leader
    0.10
    mates
    0.10
    Leader
    0.10
     trÆ°á»Łng
    0.10
     Leader
    0.09
     leaders
    0.09
     mates
    0.09
    members
    0.08
     members
    0.08
    Activations Density 0.038%

    No Known Activations