© 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. 119497
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and artistic expression

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    alink
    -0.07
    ensa
    -0.06
    dsl
    -0.06
    iger
    -0.06
    zure
    -0.06
    Happy
    -0.06
     Recorded
    -0.06
    lish
    -0.06
    reece
    -0.05
    å¨ľ
    -0.05
    POSITIVE LOGITS
     watching
    0.12
     viewing
    0.12
     reading
    0.09
    watch
    0.09
    éĺħ读
    0.09
    欣
    0.09
     watch
    0.09
     hearing
    0.09
     Watching
    0.09
    èĢ³
    0.08
    Activations Density 0.072%

    No Known Activations