© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77295
    Prev
    Next
    INDEX
    Explanations

    experiences related to military service and career progression

    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
    achel
    -0.08
    ensa
    -0.08
    arie
    -0.08
    .scalablytyped
    -0.08
    ubar
    -0.07
    attery
    -0.07
    ova
    -0.07
    ibar
    -0.07
    esi
    -0.07
    ataka
    -0.07
    POSITIVE LOGITS
    aub
    0.06
     maz
    0.06
     Technique
    0.06
     Charl
    0.06
    197
    0.06
    gie
    0.05
     Jur
    0.05
     åİ
    0.05
    οÏħ
    0.05
     yurt
    0.05
    Activations Density 0.015%

    No Known Activations