© 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. 9-LLAMASCOPE-RES-131K
    11. 94066
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and organizational partnerships

    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
    PIP
    -0.08
    rape
    -0.08
    lsen
    -0.08
     Affero
    -0.07
    enas
    -0.07
    ãĤ´ãĥª
    -0.07
    è°·
    -0.07
    byn
    -0.07
    ãĥĨãĥ«
    -0.07
    ebin
    -0.07
    POSITIVE LOGITS
    artment
    0.07
     Citizen
    0.06
     others
    0.06
     tents
    0.06
     dedic
    0.06
    acker
    0.06
     sector
    0.05
     lain
    0.05
     Baker
    0.05
     comm
    0.05
    Activations Density 0.017%

    No Known Activations