© 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. 69762
    Prev
    Next
    INDEX
    Explanations

    references to expressions of love and tribute, particularly related to mothers

    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
    erce
    -0.06
     religious
    -0.06
    608
    -0.06
     bible
    -0.06
     shit
    -0.06
     fucking
    -0.06
    218
    -0.06
    ullen
    -0.05
    dam
    -0.05
     social
    -0.05
    POSITIVE LOGITS
    hone
    0.07
    icap
    0.07
    ØŃداث
    0.07
     ÙģرÙħ
    0.07
     ÐĴлади
    0.07
     PoÄįet
    0.07
    uml
    0.07
    adden
    0.07
    ependency
    0.07
    benh
    0.07
    Activations Density 0.002%

    No Known Activations