© 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. 31607
    Prev
    Next
    INDEX
    Explanations

    phrases indicating artistic uniqueness and expression

    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
    ird
    -0.06
    opl
    -0.06
    gue
    -0.06
    âĢ¦the
    -0.06
     yourself
    -0.06
     yourselves
    -0.05
    /her
    -0.05
     ourselves
    -0.05
    ih
    -0.05
    my
    -0.05
    POSITIVE LOGITS
    å®ĥ
    0.22
     its
    0.20
    å®ĥ们
    0.20
     it
    0.19
     оно
    0.19
    ï¼Įå®ĥ
    0.19
     nó
    0.16
     Its
    0.15
    Its
    0.15
     they
    0.14
    Activations Density 0.127%

    No Known Activations