© 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. 22-LLAMASCOPE-RES-131K
    11. 4128
    Prev
    Next
    INDEX
    Explanations

    time-related information regarding transportation services

    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
    usch
    -0.08
    oub
    -0.07
    atura
    -0.07
    با
    -0.07
    382
    -0.07
    hausen
    -0.06
    ÑĭÑħ
    -0.06
    331
    -0.06
     gu
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
    sak
    0.08
     ssize
    0.07
    Unchecked
    0.06
    uten
    0.06
     Lawn
    0.06
     twice
    0.06
    Å¡em
    0.06
    Forever
    0.06
     optarg
    0.06
     ØŃدÙĬØ«
    0.06
    Activations Density 0.001%

    No Known Activations