© 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. 69389
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical lifting and heavy object handling

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    yny
    -0.06
     action
    -0.05
    ause
    -0.05
    ERO
    -0.05
    vn
    -0.05
     for
    -0.05
     background
    -0.05
     rempl
    -0.05
    vil
    -0.05
    -n
    -0.05
    POSITIVE LOGITS
    aviest
    0.09
     lifted
    0.08
    ialog
    0.08
     Kami
    0.08
     weighing
    0.08
     WEIGHT
    0.08
     Weight
    0.07
     weight
    0.07
    weigh
    0.07
    Weights
    0.07
    Activations Density 0.032%

    No Known Activations