© 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. 38477
    Prev
    Next
    INDEX
    Explanations

    terms related to the possession and ownership of weapons and illegal items

    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
    498
    -0.07
    İ·
    -0.06
    877
    -0.06
     Inherits
    -0.06
    acha
    -0.06
    egis
    -0.06
    abase
    -0.06
    ournée
    -0.06
    quat
    -0.06
     plat
    -0.06
    POSITIVE LOGITS
     proport
    0.08
    $MESS
    0.07
    ä¾Ľ
    0.07
     Schedule
    0.07
     illegally
    0.07
     nors
    0.06
    ìħľ
    0.06
    uned
    0.06
    CEED
    0.06
     secrets
    0.06
    Activations Density 0.004%

    No Known Activations