© 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. 5594
    Prev
    Next
    INDEX
    Explanations

    references to Social Security

    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
    altet
    -0.07
    CHED
    -0.07
    ä»°
    -0.06
    ibel
    -0.06
    ching
    -0.06
    大åħ¨
    -0.06
     reserve
    -0.06
    aland
    -0.06
    itled
    -0.06
    dra
    -0.06
    POSITIVE LOGITS
    byn
    0.07
    ABI
    0.06
    ViewById
    0.06
    Feed
    0.06
    bye
    0.06
    j
    0.06
    ocode
    0.06
    indsight
    0.06
    ATIVE
    0.06
    lesia
    0.06
    Activations Density 0.000%

    No Known Activations