© 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. 9-LLAMASCOPE-RES-131K
    11. 94099
    Prev
    Next
    INDEX
    Explanations

    descriptive elements of properties, particularly focusing on their appearance and landscaping features

    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
    æĹ
    -0.07
    ajaran
    -0.07
    207
    -0.07
    ewe
    -0.07
    inta
    -0.07
    ijo
    -0.07
    otle
    -0.06
    iç
    -0.06
    Occurrences
    -0.06
    ayout
    -0.06
    POSITIVE LOGITS
     Miss
    0.06
     driveway
    0.06
    arden
    0.06
    еÑĢалÑĮ
    0.06
    åį«
    0.06
    è¿İ
    0.06
    enas
    0.06
     Tib
    0.06
    èIJ
    0.05
     tar
    0.05
    Activations Density 0.034%

    No Known Activations