© 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. 53952
    Prev
    Next
    INDEX
    Explanations

    expressions of mixed emotions or contrasting opinions about a literary work

    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
    ucz
    -0.07
    umont
    -0.06
    UGIN
    -0.06
    utable
    -0.06
    çĢ
    -0.06
    ota
    -0.06
    logan
    -0.06
    arf
    -0.06
    lip
    -0.06
    @student
    -0.06
    POSITIVE LOGITS
     Abe
    0.06
    .read
    0.06
    .detach
    0.06
     spoiled
    0.06
    audi
    0.06
    ÙĤÙħ
    0.06
     Audi
    0.06
     Publisher
    0.06
     кни
    0.06
     пеÑĢеÑĤ
    0.06
    Activations Density 0.023%

    No Known Activations