© 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. 16029
    Prev
    Next
    INDEX
    Explanations

    military aircraft designations and specifications

    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
    .scalablytyped
    -0.08
     flexGrow
    -0.07
    nze
    -0.07
    [email
    -0.07
     ucwords
    -0.07
    izon
    -0.07
    TURE
    -0.07
    MBProgressHUD
    -0.07
    лки
    -0.07
    blick
    -0.07
    POSITIVE LOGITS
     abstract
    0.07
    s
    0.06
    каÑĤ
    0.06
    lint
    0.06
    -Class
    0.06
    /current
    0.05
     Abstract
    0.05
    omi
    0.05
     veniam
    0.05
     rencont
    0.05
    Activations Density 0.018%

    No Known Activations