© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88320
    Prev
    Next
    INDEX
    Explanations

    terms related to mortality and violence

    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
    rames
    -0.08
    ekim
    -0.08
    odule
    -0.08
    ntl
    -0.07
    esson
    -0.07
    ropp
    -0.07
    ivant
    -0.07
    anker
    -0.07
    lop
    -0.07
    ampo
    -0.07
    POSITIVE LOGITS
     of
    0.07
    otron
    0.06
    aton
    0.06
    VERN
    0.05
     earlier
    0.05
    AINS
    0.05
     dirt
    0.05
    BST
    0.05
     certain
    0.05
    Core
    0.05
    Activations Density 0.012%

    No Known Activations