© 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. 5-LLAMASCOPE-RES-131K
    11. 126135
    Prev
    Next
    INDEX
    Explanations

    terms related to financial waste and government spending

    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
    imar
    -0.07
    424
    -0.06
    bam
    -0.06
    ãĥĬãĥ¼
    -0.06
    份
    -0.06
    åľº
    -0.06
     voksne
    -0.06
    burgh
    -0.06
     cul
    -0.06
     unc
    -0.05
    POSITIVE LOGITS
    uru
    0.08
    leon
    0.07
    oko
    0.07
    erez
    0.07
    ennes
    0.07
    ders
    0.07
    ateur
    0.06
     wors
    0.06
    Registers
    0.06
    айÑĤ
    0.06
    Activations Density 0.003%

    No Known Activations