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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3787
    Prev
    Next
    INDEX
    Explanations

    JavaScript and asynchronous programming constructs

    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
    ritis
    -0.06
    253
    -0.06
     hone
    -0.06
    actus
    -0.06
     Bram
    -0.06
    lem
    -0.06
    erece
    -0.05
    ICTURE
    -0.05
     tik
    -0.05
     pent
    -0.05
    POSITIVE LOGITS
    rava
    0.07
    ÑĤÑĢо
    0.07
     tabi
    0.07
    bulk
    0.07
    inan
    0.07
     sÃŃ
    0.07
     Klopp
    0.07
    dale
    0.07
    strap
    0.07
    ÙĪÛĮÛĮ
    0.07
    Activations Density 0.004%

    No Known Activations