© 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. 108945
    Prev
    Next
    INDEX
    Explanations

    terms related to trends or movements, particularly those indicating upward or downward changes

    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
    luetooth
    -0.06
    eland
    -0.06
    ew
    -0.06
    lessly
    -0.06
    chooser
    -0.06
     Jennings
    -0.06
     شع
    -0.06
    yles
    -0.06
    runner
    -0.06
    790
    -0.06
    POSITIVE LOGITS
    /down
    0.13
    /up
    0.08
    -bound
    0.08
     trend
    0.07
    -down
    0.07
     bound
    0.07
    tdown
    0.07
    atoi
    0.07
    most
    0.07
    enal
    0.07
    Activations Density 0.012%

    No Known Activations