© 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. 59830
    Prev
    Next
    INDEX
    Explanations

    terms related to personal identification and privacy issues

    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
    riere
    -0.08
     Newman
    -0.07
    rière
    -0.07
     Fog
    -0.07
    usion
    -0.07
    ÑĢÑĥÑĤ
    -0.07
     prav
    -0.07
    allen
    -0.06
    ÑĢд
    -0.06
    åĿĬ
    -0.06
    POSITIVE LOGITS
     nor
    0.10
    nor
    0.07
     individual
    0.07
     personally
    0.07
    obble
    0.07
     unless
    0.07
    _individual
    0.07
     Nor
    0.07
     ê°ľìĿ¸
    0.07
    个人
    0.07
    Activations Density 0.001%

    No Known Activations