© 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. 69759
    Prev
    Next
    INDEX
    Explanations

    references to transposable elements in genetics

    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
     setting
    -0.06
     gloves
    -0.06
     Ñħол
    -0.05
     consum
    -0.05
     chambers
    -0.05
    ладÑĥ
    -0.05
     predicates
    -0.05
    ajo
    -0.05
    umed
    -0.05
     sterling
    -0.05
    POSITIVE LOGITS
    коп
    0.08
    uzzi
    0.08
    INTR
    0.07
    DBG
    0.07
     insertion
    0.07
    -insert
    0.07
     Insert
    0.06
    _runtime
    0.06
    /framework
    0.06
    $insert
    0.06
    Activations Density 0.038%

    No Known Activations