© 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. 9-LLAMASCOPE-RES-131K
    11. 96270
    Prev
    Next
    INDEX
    Explanations

    references to military surrenders and capitulations

    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
    одо
    -0.07
    AMI
    -0.07
    å·®
    -0.07
    缣
    -0.07
    iset
    -0.06
    ãĥ¼ãĥį
    -0.06
    olie
    -0.06
     Lid
    -0.06
    ami
    -0.06
     Klein
    -0.06
    POSITIVE LOGITS
    auce
    0.07
    niÄį
    0.07
    affer
    0.07
    vention
    0.06
    sky
    0.06
    á»Ļp
    0.06
    aison
    0.06
    875
    0.06
    ÎĪ
    0.06
    avers
    0.06
    Activations Density 0.011%

    No Known Activations