© 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. 59066
    Prev
    Next
    INDEX
    Explanations

    words related to social relationships and interactions

    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
     things
    -0.08
     Things
    -0.07
    /OR
    -0.06
     sooner
    -0.06
     Morav
    -0.06
    inode
    -0.06
    things
    -0.06
    çħ§
    -0.06
    irsch
    -0.06
     Bern
    -0.06
    POSITIVE LOGITS
     own
    0.14
    elves
    0.10
    zelf
    0.10
    /her
    0.10
    sing
    0.09
    -même
    0.09
    OWN
    0.09
     OWN
    0.09
    panic
    0.09
    own
    0.09
    Activations Density 0.007%

    No Known Activations