© 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. 108701
    Prev
    Next
    INDEX
    Explanations

    titles and genres related to movies and television series

    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
     Petr
    -0.06
    ãĥ£
    -0.06
    ÑģÑĤан
    -0.06
    ipher
    -0.05
     Schiff
    -0.05
     Hawaiian
    -0.05
     hazard
    -0.05
    ITA
    -0.05
    /files
    -0.05
     ******************************************************************************↵
    -0.05
    POSITIVE LOGITS
    plot
    0.09
    uzzle
    0.08
     plot
    0.08
     rated
    0.08
    Plot
    0.08
    .bc
    0.07
     Plot
    0.07
    ë£Į
    0.07
    rent
    0.07
    kul
    0.07
    Activations Density 0.014%

    No Known Activations