© 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. 57431
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to object-oriented programming

    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
     near
    -0.06
     cheap
    -0.05
    oo
    -0.05
    .truth
    -0.05
    assis
    -0.05
     heads
    -0.05
     ranger
    -0.05
    oci
    -0.05
    urum
    -0.05
     Ranger
    -0.05
    POSITIVE LOGITS
    benh
    0.09
    .prototype
    0.08
    anio
    0.08
     Tie
    0.07
    .java
    0.07
    继
    0.07
    ibase
    0.07
    ìĿ´ìŀIJ
    0.07
    γε
    0.07
    IOC
    0.07
    Activations Density 0.001%

    No Known Activations