© 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. 57108
    Prev
    Next
    INDEX
    Explanations

    phrases related to processing and duration of financial transactions

    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
     addCriterion
    -0.08
     Dün
    -0.07
    obia
    -0.07
    .openg
    -0.07
    alfa
    -0.07
    .AWS
    -0.07
    qli
    -0.07
     showc
    -0.07
    ANDLE
    -0.07
    κει
    -0.07
    POSITIVE LOGITS
     processing
    0.08
     approximately
    0.06
     s
    0.06
     carbon
    0.06
     Processing
    0.06
    uro
    0.06
     typically
    0.06
    Processing
    0.06
    processing
    0.06
     lag
    0.06
    Activations Density 0.017%

    No Known Activations