© 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. 108928
    Prev
    Next
    INDEX
    Explanations

    mentions of memorial contributions and charitable donations

    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
    essed
    -0.07
    istar
    -0.06
     ÎłÏģÏī
    -0.06
    imus
    -0.06
    regor
    -0.06
    antz
    -0.06
    istinguished
    -0.06
    anders
    -0.06
    _prov
    -0.06
    TexParameteri
    -0.06
    POSITIVE LOGITS
    DataExchange
    0.07
    ัà¸įà¸į
    0.06
    éĬ
    0.06
    ableView
    0.06
     family
    0.06
    LayoutConstraint
    0.06
    ór
    0.06
    GenerationStrategy
    0.06
    á»ĵng
    0.06
    SetBranch
    0.06
    Activations Density 0.001%

    No Known Activations