© 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. 28761
    Prev
    Next
    INDEX
    Explanations

    terms related to economic metrics and foreign trade dynamics

    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
    fur
    -0.06
    rof
    -0.06
    @mail
    -0.06
    .bam
    -0.06
     fur
    -0.06
     âĸĪ
    -0.06
     retrieval
    -0.06
     wash
    -0.06
     bail
    -0.06
     idi
    -0.06
    POSITIVE LOGITS
    indicator
    0.10
     indicator
    0.08
    xies
    0.08
     variables
    0.08
    undry
    0.08
    à¸ĩà¸ģ
    0.07
     lag
    0.07
    åĿĤ
    0.07
    lag
    0.07
    Dummy
    0.07
    Activations Density 0.024%

    No Known Activations