© 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 EvalsExportsAPI 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. 56212
    Prev
    Next
    INDEX
    Explanations

    instances of trauma and loss

    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
    iti
    -0.08
    earch
    -0.07
    jang
    -0.07
    lsi
    -0.07
     omn
    -0.06
    pson
    -0.06
    ombat
    -0.06
    riel
    -0.06
    ARP
    -0.06
    638
    -0.06
    POSITIVE LOGITS
    amer
    0.07
    åį·
    0.06
    éħ
    0.06
    .Virtual
    0.06
    رÛĮاÙĨ
    0.06
    UDGE
    0.06
     polluted
    0.06
    -transparent
    0.06
    Handled
    0.06
    .sav
    0.06
    Activations Density 0.018%

    No Known Activations