© 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. 89684
    Prev
    Next
    INDEX
    Explanations

    actions related to physical contact or touching

    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
    mouth
    -0.08
    umar
    -0.07
    缼
    -0.07
    iem
    -0.07
    amik
    -0.07
    ãĥ³ãĥĸ
    -0.07
    oral
    -0.07
    Ñħо
    -0.07
     pozor
    -0.06
    ÑĢиÑĩ
    -0.06
    POSITIVE LOGITS
     rub
    0.10
     rubbing
    0.09
     rubbed
    0.09
     Rub
    0.08
     Mills
    0.07
    rub
    0.07
    beck
    0.07
     friction
    0.07
     Bella
    0.06
     across
    0.06
    Activations Density 0.006%

    No Known Activations