© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97524
    Prev
    Next
    INDEX
    Explanations

    phrases related to government involvement and 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
     bis
    -0.07
    inho
    -0.07
    sted
    -0.07
    lsru
    -0.06
    .Restrict
    -0.06
    iant
    -0.06
     Bis
    -0.06
    recated
    -0.06
    reh
    -0.06
    ¬Ĥ
    -0.06
    POSITIVE LOGITS
    ema
    0.08
    AMA
    0.07
    .uk
    0.07
    .big
    0.07
    enberg
    0.07
    ัà¸įà¸į
    0.06
    elite
    0.06
    ERAL
    0.06
    λεκ
    0.06
     ciz
    0.06
    Activations Density 0.030%

    No Known Activations