© 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. 121545
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and planning for the future

    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
    ĥn
    -0.07
     Mitt
    -0.06
    太éĥİ
    -0.06
    101
    -0.06
     Canary
    -0.06
    延
    -0.06
    æ´
    -0.06
     Conte
    -0.06
     sophisticated
    -0.05
    aka
    -0.05
    POSITIVE LOGITS
    COPE
    0.08
    &action
    0.08
    ayıp
    0.08
    niž
    0.08
    cla
    0.08
    tahun
    0.07
    adia
    0.07
    ê¸°ë¡ľ
    0.07
    avern
    0.07
    orpion
    0.07
    Activations Density 0.001%

    No Known Activations