© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29583
    Prev
    Next
    INDEX
    Explanations

    references to ancient methods of counting and economic interactions, particularly those related to taxation and land ownership

    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
    chwitz
    -0.07
    azer
    -0.07
    íĸ¥
    -0.07
    ìĤ¬ê°Ģ
    -0.07
     yesterday
    -0.06
     Yesterday
    -0.06
    abr
    -0.06
    etur
    -0.06
    ,www
    -0.06
    crate
    -0.06
    POSITIVE LOGITS
     taxes
    0.09
     tribute
    0.08
     tax
    0.08
    tribute
    0.07
     lev
    0.07
     Taxes
    0.07
     tre
    0.07
    814
    0.07
     annually
    0.07
    å®ĺ
    0.07
    Activations Density 0.035%

    No Known Activations