© 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. 121645
    Prev
    Next
    INDEX
    Explanations

    terms related to photography and its rules or restrictions in art galleries

    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
    avors
    -0.06
     numberWith
    -0.06
    ácil
    -0.06
    omal
    -0.06
    acer
    -0.06
    ahlen
    -0.06
     Enemies
    -0.06
     actionTypes
    -0.06
    ør
    -0.06
    riott
    -0.06
    POSITIVE LOGITS
    allowed
    0.11
     forbidden
    0.10
     allowed
    0.10
    Allowed
    0.10
     permitted
    0.10
     Allowed
    0.10
    .rules
    0.09
     rules
    0.09
    rules
    0.09
     restriction
    0.09
    Activations Density 0.048%

    No Known Activations