© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5799
    Prev
    Next
    INDEX
    Explanations

    emotional and physical reactions related to intimacy and vulnerability

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    fty
    -0.07
    iye
    -0.06
    oria
    -0.06
    iec
    -0.06
     brand
    -0.06
    crypto
    -0.06
    workflow
    -0.06
    åde
    -0.06
    downloads
    -0.05
     fetched
    -0.05
    POSITIVE LOGITS
    lü
    0.07
    brick
    0.06
    ác
    0.06
     HOLDER
    0.06
     HOLDERS
    0.06
    bson
    0.06
    jos
    0.06
    aber
    0.06
     raÄŁmen
    0.06
    å°ij女
    0.06
    Activations Density 0.038%

    No Known Activations