© 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. 70706
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion and statements about safety in sports

    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
    stadt
    -0.07
    ibold
    -0.07
    izzo
    -0.07
     Eag
    -0.07
    ợ
    -0.06
    Decoration
    -0.06
    istro
    -0.06
    iez
    -0.06
    baÅŁ
    -0.06
    éİ®
    -0.06
    POSITIVE LOGITS
    rink
    0.06
    æ²¢
    0.06
    âĦ
    0.06
    enh
    0.06
    895
    0.06
    ibaba
    0.06
    ä¼¼
    0.06
    uro
    0.06
     Ej
    0.06
    _requires
    0.06
    Activations Density 0.005%

    No Known Activations