© 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 EvalsExportsAPI 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. 130424
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to liability and culpability

    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
    anzi
    -0.08
    rozen
    -0.08
    inkel
    -0.08
    ybrid
    -0.07
    าะ
    -0.07
    statuses
    -0.07
     addCriterion
    -0.07
    eer
    -0.07
    eated
    -0.06
     blackmail
    -0.06
    POSITIVE LOGITS
     intentional
    0.12
     deliberate
    0.11
     care
    0.08
     intentionally
    0.08
     reck
    0.08
     negligence
    0.08
     wil
    0.07
     deliberately
    0.07
     mal
    0.07
     intent
    0.07
    Activations Density 0.113%

    No Known Activations