© 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. 127103
    Prev
    Next
    INDEX
    Explanations

    phrases related to duration and conditions regarding requests or actions

    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
    berger
    -0.07
    reste
    -0.07
     Seeder
    -0.07
    ãĥ¼ãĥĪ
    -0.07
    prog
    -0.07
    	Copyright
    -0.07
    _Delay
    -0.07
    spender
    -0.07
    Intialized
    -0.07
    esses
    -0.07
    POSITIVE LOGITS
     either
    0.10
     Either
    0.07
     Burl
    0.07
     EITHER
    0.07
    Either
    0.06
     explicit
    0.06
    either
    0.06
    explicit
    0.06
     Explicit
    0.06
     Lane
    0.06
    Activations Density 0.017%

    No Known Activations