© 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. 27294
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to various types of insurance

    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
     exposition
    -0.07
     ãĢ
    -0.06
    ingham
    -0.06
    INGTON
    -0.06
    ENCH
    -0.06
     Tray
    -0.05
    aghan
    -0.05
     mark
    -0.05
    aurus
    -0.05
    ENCIL
    -0.05
    POSITIVE LOGITS
    coverage
    0.09
     coverage
    0.08
     cover
    0.08
    cover
    0.08
    Coverage
    0.07
    _coverage
    0.07
     Coverage
    0.07
    atego
    0.07
    COVER
    0.07
    ector
    0.07
    Activations Density 0.004%

    No Known Activations