© 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. 118218
    Prev
    Next
    INDEX
    Explanations

    references to the impact of life and death situations on individuals and their rights

    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
    ezier
    -0.08
    меÑĤÑĮ
    -0.07
     escal
    -0.07
    ois
    -0.07
    rench
    -0.07
    lav
    -0.07
    EMP
    -0.07
    ulia
    -0.07
     inval
    -0.07
    olis
    -0.07
    POSITIVE LOGITS
     bottoms
    0.06
    aki
    0.06
    aru
    0.06
     margin
    0.06
    волÑı
    0.05
    440
    0.05
    лÑĸн
    0.05
     Seb
    0.05
     Ek
    0.05
     akt
    0.05
    Activations Density 0.052%

    No Known Activations