© 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. 105759
    Prev
    Next
    INDEX
    Explanations

    statistics and alarming findings regarding safety and health concerns

    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
    ijd
    -0.09
    ichick
    -0.07
    SystemService
    -0.07
     incididunt
    -0.07
     incel
    -0.07
    äll
    -0.07
    ÃŃg
    -0.07
    .='
    -0.06
    öl
    -0.06
    inus
    -0.06
    POSITIVE LOGITS
     knowledge
    0.08
     awareness
    0.07
     quiz
    0.07
     ignorance
    0.07
     correct
    0.06
    çŁ¥è¯Ĩ
    0.06
     Knowledge
    0.06
     fame
    0.06
     answers
    0.06
    knowledge
    0.06
    Activations Density 0.006%

    No Known Activations