© 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. 15-LLAMASCOPE-RES-131K
    11. 89903
    Prev
    Next
    INDEX
    Explanations

    instances of political figures and their actions or discussions

    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
    aload
    -0.08
    vale
    -0.08
    utex
    -0.08
    frauen
    -0.08
    nda
    -0.07
    ÑĢÑĸп
    -0.07
    preg
    -0.07
    ordova
    -0.07
    filme
    -0.07
    ijing
    -0.07
    POSITIVE LOGITS
    s
    0.06
    ikat
    0.06
     town
    0.06
     Wes
    0.06
     NPR
    0.05
     increment
    0.05
     engineering
    0.05
     har
    0.05
     somehow
    0.05
    529
    0.05
    Activations Density 0.001%

    No Known Activations