© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 94751
    Prev
    Next
    INDEX
    Explanations

    references to specific violent incidents and their details

    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
     extrad
    -0.07
     Giang
    -0.07
    pgsql
    -0.06
     Bordeaux
    -0.06
    errated
    -0.06
    fty
    -0.06
    pear
    -0.06
    aussian
    -0.06
     extradition
    -0.06
     extr
    -0.06
    POSITIVE LOGITS
    lando
    0.07
     Orlando
    0.07
    /assert
    0.06
    ayar
    0.06
    cyan
    0.06
    gay
    0.06
     Normalize
    0.06
    .Transport
    0.06
    _sphere
    0.06
     Marketplace
    0.06
    Activations Density 0.003%

    No Known Activations