© 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. 27096
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to music industry trends

    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
    ávÄĽ
    -0.06
    еди
    -0.06
    jax
    -0.05
    ãĤĬãģ¨
    -0.05
     Wise
    -0.05
    ãĥ«ãĥī
    -0.05
    É
    -0.05
     Rud
    -0.05
     Means
    -0.05
    viron
    -0.05
    POSITIVE LOGITS
    000
    0.13
    0
    0.11
    00
    0.10
    Û°Û°Û°
    0.08
    zyst
    0.08
    -Semit
    0.08
    Ĥæķ°
    0.07
    edata
    0.07
    à¹IJ
    0.07
    iou
    0.07
    Activations Density 0.017%

    No Known Activations