© 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. 119036
    Prev
    Next
    INDEX
    Explanations

    references to economic statistics and conditions

    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
     disap
    -0.08
    ManagerInterface
    -0.07
    fty
    -0.07
    /Instruction
    -0.07
     dosy
    -0.07
    eyi
    -0.07
    تÙĩ
    -0.07
    ovÃŃ
    -0.07
    orr
    -0.07
    Ñĸп
    -0.06
    POSITIVE LOGITS
     unemployment
    0.07
    rej
    0.06
     Consumer
    0.06
    gang
    0.06
    0.06
     port
    0.06
     Stat
    0.06
    alcon
    0.06
     derivative
    0.06
     reports
    0.06
    Activations Density 0.016%

    No Known Activations