© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89420
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express uncertainty or prerequisites

    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
    orro
    -0.07
    .jp
    -0.07
    orda
    -0.06
     Lama
    -0.06
    anga
    -0.06
    idy
    -0.06
    abyrinth
    -0.06
    _sid
    -0.06
    uga
    -0.06
     breakpoint
    -0.06
    POSITIVE LOGITS
     already
    0.17
    already
    0.15
     Already
    0.14
    Already
    0.13
    å·²ç»ı
    0.10
     Ñĥже
    0.10
     schon
    0.10
     giÃł
    0.10
     már
    0.09
    _already
    0.09
    Activations Density 0.011%

    No Known Activations