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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30594
    Prev
    Next
    INDEX
    Explanations

    questions and conditional statements related to insurance and safety

    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
     ìŬ룬ë¶Ħ
    -0.07
    %X
    -0.06
     Chap
    -0.06
    uppen
    -0.06
    pip
    -0.06
     subsid
    -0.06
    ôme
    -0.06
     sometimes
    -0.06
    .bin
    -0.06
    ürk
    -0.06
    POSITIVE LOGITS
     Voj
    0.07
    444
    0.07
    uch
    0.07
    onth
    0.07
     my
    0.07
     è»Ĭ
    0.07
     meu
    0.07
    ç»ĻæĪij
    0.07
    ãģĹãģŁãĤī
    0.06
    ught
    0.06
    Activations Density 0.031%

    No Known Activations