© 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 EvalsExportsinterp-engineNEWAPI 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. 5461
    Prev
    Next
    INDEX
    Explanations

    references to specific age groups, particularly young individuals

    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
    лиÑĪком
    -0.09
    ernes
    -0.09
     Torch
    -0.09
    hod
    -0.08
    одеÑĢж
    -0.08
    eor
    -0.08
    ££
    -0.08
    isay
    -0.08
    ulum
    -0.08
    ropp
    -0.08
    POSITIVE LOGITS
     age
    0.09
     tuá»ķi
    0.08
     Age
    0.06
     to
    0.06
    -to
    0.06
    Âł
    0.06
    (age
    0.06
     g
    0.06
     amen
    0.05
     ch
    0.05
    Activations Density 0.008%

    No Known Activations