© 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. 15-LLAMASCOPE-RES-131K
    11. 541
    Prev
    Next
    INDEX
    Explanations

    discussions related to crime and its prevention

    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
     VÅ¡ech
    -0.10
     blas
    -0.08
    ëĿ¼ë§Ī
    -0.08
    ฯ
    -0.08
    adb
    -0.08
     boj
    -0.08
    /includes
    -0.08
    .omg
    -0.08
    име
    -0.08
    kb
    -0.08
    POSITIVE LOGITS
     I
    0.07
    âĢ¦↵
    0.07
    ÂŃi
    0.06
     myself
    0.06
     [âĢ¦]↵
    0.06
     observe
    0.06
    úsqueda
    0.06
     Harvey
    0.06
    âĢ¦
    0.05
    âĢ¦”
    0.05
    Activations Density 5.220%

    No Known Activations