© 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. 15-LLAMASCOPE-RES-131K
    11. 27356
    Prev
    Next
    INDEX
    Explanations

    references to prisoners and hostages in various contexts, particularly focusing on their experiences and conditions

    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
    ajan
    -0.07
    roperties
    -0.07
     пÑĢиÑĩ
    -0.07
    arga
    -0.07
    dez
    -0.06
    ipop
    -0.06
    ase
    -0.06
    ROC
    -0.06
    tual
    -0.06
    IRT
    -0.06
    POSITIVE LOGITS
    hood
    0.08
    /sl
    0.07
    èĻ
    0.07
    .release
    0.07
    /release
    0.07
    -taking
    0.06
    ries
    0.06
     ÙĪاÙĦع
    0.06
     Dane
    0.06
     Seas
    0.06
    Activations Density 0.014%

    No Known Activations