© 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. 74263
    Prev
    Next
    INDEX
    Explanations

    mentions of the Paralympic Games and related achievements

    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
    ÅĪ
    -0.08
    祥
    -0.07
    าà¸ĩว
    -0.06
    нив
    -0.06
    æŁĦ
    -0.06
    ettel
    -0.06
    usch
    -0.06
     Robbie
    -0.06
    appy
    -0.06
    bette
    -0.06
    POSITIVE LOGITS
    ingen
    0.07
    redient
    0.07
    oma
    0.07
    oriously
    0.07
     bang
    0.06
    cue
    0.06
    169
    0.06
    ÙĦÙĦ
    0.06
    ale
    0.06
    zh
    0.06
    Activations Density 0.000%

    No Known Activations