© 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. 63232
    Prev
    Next
    INDEX
    Explanations

    terms related to slopes and their properties

    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
    lsen
    -0.07
    raq
    -0.07
    list
    -0.07
    lad
    -0.07
    lin
    -0.06
    role
    -0.06
    ikel
    -0.06
    lot
    -0.06
    zers
    -0.06
     Ames
    -0.06
    POSITIVE LOGITS
    stakes
    0.08
    itzer
    0.08
    sters
    0.08
    side
    0.07
    peare
    0.07
    oenix
    0.07
    aroo
    0.07
    ertino
    0.07
    ycastle
    0.07
    ster
    0.07
    Activations Density 0.006%

    No Known Activations