© 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. 18837
    Prev
    Next
    INDEX
    Explanations

    criteria related to licensing and insurance requirements

    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
    Accessory
    -0.07
    ACA
    -0.07
    пÑĢимеÑĢ
    -0.07
    arak
    -0.07
    asmus
    -0.07
    elter
    -0.06
    RenderingContext
    -0.06
    arrants
    -0.06
    storybook
    -0.06
     Pand
    -0.06
    POSITIVE LOGITS
     liability
    0.10
     Liability
    0.10
     coverage
    0.08
     defense
    0.08
     claims
    0.08
    coverage
    0.08
    -li
    0.08
     LIABILITY
    0.07
     defenses
    0.07
     liabilities
    0.07
    Activations Density 0.026%

    No Known Activations