© 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. 15106
    Prev
    Next
    INDEX
    Explanations

    references to pain, loss, and emotional struggles

    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
     Trend
    -0.06
     羣
    -0.06
    羣
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
     closure
    -0.06
    indsight
    -0.05
     Kits
    -0.05
    ible
    -0.05
     adopt
    -0.05
    оÑĢм
    -0.05
    POSITIVE LOGITS
     Singular
    0.07
     MaterialPageRoute
    0.07
    WithIdentifier
    0.07
    彡
    0.07
    æ¦
    0.07
    /epl
    0.07
    λήÏĤ
    0.07
    ernetes
    0.06
    svc
    0.06
    až
    0.06
    Activations Density 0.043%

    No Known Activations