© 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. 15-LLAMASCOPE-RES-131K
    11. 86089
    Prev
    Next
    INDEX
    Explanations

    instances of contrasted costs or sacrifices involved in various scenarios

    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
    @@
    -0.06
    inan
    -0.06
    li
    -0.06
    tog
    -0.06
    er
    -0.06
    ByExample
    -0.06
    trl
    -0.05
    -mouth
    -0.05
    /F
    -0.05
    att
    -0.05
    POSITIVE LOGITS
    éric
    0.07
    GuidId
    0.07
    æİī
    0.07
    angers
    0.07
    çĬ
    0.07
    loat
    0.07
    اÛĮØ´
    0.07
    ereo
    0.07
    RuntimeObject
    0.07
    277
    0.07
    Activations Density 0.005%

    No Known Activations