© 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. 17-LLAMASCOPE-RES-131K
    11. 27434
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal aspirations and societal expectations

    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
     Wish
    -0.07
     Sanity
    -0.07
    wish
    -0.07
    urma
    -0.07
    inya
    -0.06
    lio
    -0.06
    ãĥ¼ãĤ¯
    -0.06
    269
    -0.06
    avi
    -0.06
    unya
    -0.06
    POSITIVE LOGITS
     expectation
    0.07
     EXPECT
    0.07
     believe
    0.07
    expect
    0.07
    Expect
    0.07
     expectancy
    0.06
     believing
    0.06
     believes
    0.06
     expect
    0.06
    Ñľ
    0.06
    Activations Density 0.032%

    No Known Activations