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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 126696
    Prev
    Next
    INDEX
    Explanations

    concepts related to privatization and government intervention in the economy

    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
    ects
    -0.07
    wei
    -0.06
    ray
    -0.06
    SEC
    -0.06
    antino
    -0.06
    PGA
    -0.06
     Suzuki
    -0.05
    ect
    -0.05
     plastic
    -0.05
    gars
    -0.05
    POSITIVE LOGITS
     ownership
    0.09
     privat
    0.08
    Ownership
    0.08
     priv
    0.08
     Ownership
    0.08
    ownership
    0.07
     monopoly
    0.07
    avern
    0.07
    odox
    0.07
     monopol
    0.07
    Activations Density 0.062%

    No Known Activations