© 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. 15-LLAMASCOPE-RES-131K
    11. 86057
    Prev
    Next
    INDEX
    Explanations

    references to company structures and organizational 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
    rá
    -0.07
     kem
    -0.06
    ÙĪÙĦÙĩ
    -0.06
    roduce
    -0.06
     Rag
    -0.06
    utin
    -0.06
    оз
    -0.06
     Braun
    -0.06
    eson
    -0.06
    agh
    -0.06
    POSITIVE LOGITS
     previous
    0.12
     previously
    0.12
     replaces
    0.11
    Previously
    0.10
     replacing
    0.10
    previous
    0.10
     Previously
    0.10
    .previous
    0.10
     replace
    0.10
     formerly
    0.10
    Activations Density 0.175%

    No Known Activations