© 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. 9-LLAMASCOPE-RES-131K
    11. 94272
    Prev
    Next
    INDEX
    Explanations

    elements that describe locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     fore
    -0.07
    andard
    -0.06
    ocracy
    -0.06
    ams
    -0.06
    otten
    -0.06
    uctor
    -0.06
    izen
    -0.06
    unction
    -0.06
    ut
    -0.06
    lund
    -0.06
    POSITIVE LOGITS
    .pretty
    0.07
    leigh
    0.07
    ÎŃÏģ
    0.07
    åį«
    0.07
    _ios
    0.07
    ANNOT
    0.07
    iges
    0.07
     íĭ
    0.07
    âĢ¦.↵↵
    0.07
    iggs
    0.07
    Activations Density 0.012%

    No Known Activations