© 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. 86134
    Prev
    Next
    INDEX
    Explanations

    expressions of expectation or prediction

    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
    uer
    -0.07
    atus
    -0.07
    agan
    -0.07
    UTE
    -0.06
    gan
    -0.06
    inger
    -0.06
    avir
    -0.06
    oto
    -0.06
    apolis
    -0.06
    arn
    -0.06
    POSITIVE LOGITS
     expected
    0.23
     expecting
    0.21
     expectation
    0.21
     expectations
    0.20
    expected
    0.18
     Expected
    0.18
    expect
    0.18
     EXPECT
    0.18
     expect
    0.18
     expects
    0.17
    Activations Density 0.072%

    No Known Activations