© 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. 82187
    Prev
    Next
    INDEX
    Explanations

    information related to military ships and submarines

    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
    aeda
    -0.07
    arsers
    -0.07
    иж
    -0.07
    vfs
    -0.07
    rana
    -0.07
     Indust
    -0.07
    stash
    -0.06
    pNet
    -0.06
    rej
    -0.06
     bail
    -0.06
    POSITIVE LOGITS
     Hamm
    0.06
     Hood
    0.06
    ãĤħ
    0.06
    US
    0.06
     stoi
    0.06
    ieri
    0.06
    Mixin
    0.06
     Rounds
    0.06
     escort
    0.06
     hamm
    0.06
    Activations Density 0.004%

    No Known Activations