© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96205
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to age and quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    enstein
    -0.06
    lands
    -0.06
    /MIT
    -0.06
    kees
    -0.06
    ÑĸÑĶ
    -0.06
    eza
    -0.06
    ile
    -0.06
    iá»ĩn
    -0.06
    uters
    -0.06
    257
    -0.06
    POSITIVE LOGITS
    etheless
    0.07
     ago
    0.07
    etically
    0.07
    ëĵľë¦¬
    0.07
    ÅĻi
    0.07
    нак
    0.07
    aris
    0.06
    thesize
    0.06
     members
    0.06
    thed
    0.06
    Activations Density 0.018%

    No Known Activations