© 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. 121654
    Prev
    Next
    INDEX
    Explanations

    references to influence and relationships between entities

    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
    uet
    -0.08
    OUGH
    -0.07
    uml
    -0.07
    ogui
    -0.07
    uant
    -0.07
    vier
    -0.07
    shal
    -0.06
    adolu
    -0.06
    ubu
    -0.06
    obra
    -0.06
    POSITIVE LOGITS
     vice
    0.14
    vice
    0.11
     Vice
    0.10
     recip
    0.09
     receive
    0.07
    Receive
    0.07
    ë°Ľ
    0.07
    .Receive
    0.07
    éĸĵ
    0.07
     Receive
    0.07
    Activations Density 0.039%

    No Known Activations