© 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. 89625
    Prev
    Next
    INDEX
    Explanations

    expressions of connection and empathy

    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
    urf
    -0.07
    :checked
    -0.07
    coe
    -0.06
     Bere
    -0.06
    çĨ
    -0.06
    çĢ
    -0.06
     fseek
    -0.06
    墨
    -0.06
    praak
    -0.06
     Loose
    -0.06
    POSITIVE LOGITS
    izyon
    0.07
     suddenly
    0.06
     moment
    0.06
    wash
    0.06
    imers
    0.06
    åĿª
    0.06
     felt
    0.06
    اص
    0.06
    eton
    0.06
     abs
    0.06
    Activations Density 0.047%

    No Known Activations