© 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. 81710
    Prev
    Next
    INDEX
    Explanations

    references to charitable organizations and medical research initiatives

    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
     Gross
    -0.07
     gross
    -0.07
    gross
    -0.06
    li
    -0.06
    -0.06
    enance
    -0.06
    oho
    -0.06
     (
    -0.06
    elop
    -0.05
    yas
    -0.05
    POSITIVE LOGITS
     tsl
    0.07
    cers
    0.07
    лаÑĤи
    0.07
     оÑĢганÑĸзаÑĨÑĸÑĹ
    0.07
    oggler
    0.07
    GLOBALS
    0.07
    .tc
    0.07
     Crisis
    0.07
     causes
    0.07
     оÑĢганизаÑĨии
    0.07
    Activations Density 0.021%

    No Known Activations