© 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. 89731
    Prev
    Next
    INDEX
    Explanations

    elements related to mystery and intrigue

    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
     Ebony
    -0.07
    åĤ
    -0.07
    562
    -0.06
     Jacob
    -0.06
    loud
    -0.06
    245
    -0.06
    ombine
    -0.06
    esser
    -0.06
    ap
    -0.06
    ells
    -0.06
    POSITIVE LOGITS
     mystery
    0.17
     legend
    0.14
     mysteries
    0.13
     mysterious
    0.12
     legends
    0.12
     myst
    0.12
     Mystery
    0.12
    legend
    0.10
    ystery
    0.10
     Legend
    0.09
    Activations Density 0.046%

    No Known Activations