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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3952
    Prev
    Next
    INDEX
    Explanations

    questions and information related to train schedules and travel between cities

    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
     Congress
    -0.07
    oren
    -0.06
    ngen
    -0.06
     Transportation
    -0.06
     dut
    -0.06
    ewis
    -0.06
    enso
    -0.06
    ertiary
    -0.06
     Transport
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
     arrives
    0.08
    áp
    0.07
    aci
    0.07
    ople
    0.07
    ivr
    0.07
    ánt
    0.07
    chez
    0.07
     cÃŃ
    0.06
     sona
    0.06
    inkle
    0.06
    Activations Density 0.003%

    No Known Activations