© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 120926
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceeding or surpassing 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
    kode
    -0.07
    ismet
    -0.07
    UGE
    -0.07
    kes
    -0.07
    Äįel
    -0.07
    rong
    -0.07
    zure
    -0.06
    correct
    -0.06
    ugu
    -0.06
    ÄĻd
    -0.06
    POSITIVE LOGITS
     expectations
    0.16
     expectation
    0.12
     Expect
    0.12
    expect
    0.10
     expect
    0.09
     expects
    0.09
    Expect
    0.09
     standards
    0.08
    (expect
    0.08
     EXPECT
    0.08
    Activations Density 0.003%

    No Known Activations