© 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. 94045
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives indicative of regions, conditions, or emotional states

    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
    istrovstvÃŃ
    -0.08
    umin
    -0.07
    anager
    -0.07
    ibling
    -0.07
    idon
    -0.07
    ,www
    -0.07
    _DC
    -0.07
    à¥Īà¤ļ
    -0.07
    arning
    -0.06
     вд
    -0.06
    POSITIVE LOGITS
    sto
    0.06
    nees
    0.06
    ãĥ³ãĥĢ
    0.06
    latex
    0.06
    İ
    0.06
     economics
    0.06
    ses
    0.06
    elman
    0.06
    se
    0.05
    Mathf
    0.05
    Activations Density 0.380%

    No Known Activations