© 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. 89737
    Prev
    Next
    INDEX
    Explanations

    keywords related to cultural or artistic contexts

    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
    rocket
    -0.07
    ÑĪе
    -0.07
    ãĤµãĤ¤
    -0.07
    à¸ĵà¸ij
    -0.07
     Sür
    -0.07
    ÑĢÑĥж
    -0.07
    ủ
    -0.07
    udit
    -0.07
    asn
    -0.07
    Ìī
    -0.07
    POSITIVE LOGITS
    eldorf
    0.06
    anning
    0.06
    icum
    0.05
    ye
    0.05
    ness
    0.05
     ste
    0.05
    âĸĪ
    0.05
    occus
    0.05
     IReadOnly
    0.05
    scope
    0.05
    Activations Density 0.007%

    No Known Activations