© 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. 42561
    Prev
    Next
    INDEX
    Explanations

    critiques focusing on character development and the depth of narrative elements

    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
    ripper
    -0.08
    osu
    -0.07
    amment
    -0.07
     kaf
    -0.07
    .EntityFramework
    -0.07
    unks
    -0.07
    rips
    -0.07
    dle
    -0.07
    iams
    -0.06
     ëĭ¬
    -0.06
    POSITIVE LOGITS
     disappointing
    0.11
     disappoint
    0.09
     fails
    0.09
     fail
    0.09
    forgettable
    0.08
     merely
    0.08
     FAIL
    0.08
     simply
    0.08
     instead
    0.07
     failed
    0.07
    Activations Density 0.031%

    No Known Activations