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

    Neuronpedia

    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. 77676
    Prev
    Next
    INDEX
    Explanations

    terms related to legal penalties and punishments

    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
     Impossible
    -0.06
    Impossible
    -0.06
    oth
    -0.05
    -running
    -0.05
     hij
    -0.05
    263
    -0.05
     Infer
    -0.05
     Eaton
    -0.05
     Lum
    -0.05
     Wil
    -0.05
    POSITIVE LOGITS
     punishments
    0.09
     punishment
    0.09
    ç½ļ
    0.09
    pun
    0.08
     deterrent
    0.08
     phạt
    0.08
     severity
    0.08
     penalties
    0.08
    FINE
    0.08
    á»ķi
    0.07
    Activations Density 0.036%

    No Known Activations