© 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. 127138
    Prev
    Next
    INDEX
    Explanations

    laws concerning legality and regulations associated with criminal activities

    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
    arg
    -0.07
    2
    -0.06
    -0.06
    Central
    -0.06
    end
    -0.06
    eba
    -0.05
     middle
    -0.05
     Premium
    -0.05
     premium
    -0.05
     Central
    -0.05
    POSITIVE LOGITS
     Cumhur
    0.09
    ancode
    0.08
    affen
    0.08
    éĻ
    0.08
    STRU
    0.08
    assi
    0.07
    ÑĢаÐ
    0.07
    íĨłíĨł
    0.07
     Ding
    0.07
    ëį°ìĿ´íĬ¸
    0.07
    Activations Density 0.037%

    No Known Activations