© 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. 53743
    Prev
    Next
    INDEX
    Explanations

    corporate and organizational references in the context of research and development

    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
    ookie
    -0.07
    ije
    -0.07
    incr
    -0.07
    νÏĦ
    -0.06
    igham
    -0.06
    amu
    -0.06
    hdl
    -0.06
    olla
    -0.06
    amel
    -0.06
     MouseButton
    -0.06
    POSITIVE LOGITS
    ÙĪÙĦÙĬ
    0.06
     Cli
    0.06
    èĮĤ
    0.06
    onte
    0.06
    oute
    0.06
     clearColor
    0.06
    514
    0.06
    ollapsed
    0.06
     Laurent
    0.06
    à¸Ļาม
    0.06
    Activations Density 0.007%

    No Known Activations