© 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. 92781
    Prev
    Next
    INDEX
    Explanations

    references to the concept of love, particularly in cultural and event contexts

    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
    ÎŃÏģγ
    -0.08
    ness
    -0.07
    ải
    -0.07
    ãĥ³ãĥIJãĥ¼
    -0.07
    staw
    -0.07
    dy
    -0.07
    modation
    -0.06
    remen
    -0.06
    á»ijt
    -0.06
    skb
    -0.06
    POSITIVE LOGITS
    able
    0.10
    ably
    0.09
    full
    0.08
    lessly
    0.08
    fully
    0.07
    craft
    0.07
    leigh
    0.07
     affair
    0.07
    ABLE
    0.06
     ÙĪرز
    0.06
    Activations Density 0.022%

    No Known Activations