© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106112
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and parameters, particularly in code contexts

    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
    .openConnection
    -0.08
    ÏĦεÏį
    -0.07
    oute
    -0.07
    >(*
    -0.07
    aeda
    -0.07
    ayette
    -0.07
    -deals
    -0.07
    .imgur
    -0.07
    ActionCreators
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     or
    0.09
    ?.
    0.09
     if
    0.08
    !=
    0.08
    ?
    0.08
     !=
    0.08
     assertNotNull
    0.08
     &&
    0.07
     ||=
    0.07
    if
    0.07
    Activations Density 0.072%

    No Known Activations