© 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. 18742
    Prev
    Next
    INDEX
    Explanations

    features and amenities of hotels and accommodations

    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
     hereby
    -0.06
     Lond
    -0.06
    irit
    -0.06
     dem
    -0.06
    /her
    -0.06
    leo
    -0.06
     releg
    -0.06
     erotische
    -0.05
    iker
    -0.05
     tang
    -0.05
    POSITIVE LOGITS
    .FontStyle
    0.07
    istrovstvÃŃ
    0.07
    ãĥ¼ãĥijãĥ¼
    0.07
    инок
    0.07
    úsqueda
    0.07
    .CompareTag
    0.06
    entiful
    0.06
    íģ
    0.06
    :"-
    0.06
    .staff
    0.06
    Activations Density 0.007%

    No Known Activations