© 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. 119563
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs, particularly those involving structures and configurations

    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
     Kick
    -0.06
     Maj
    -0.06
     cra
    -0.06
    izzo
    -0.06
     Ron
    -0.06
    uncio
    -0.06
    acades
    -0.06
    ombres
    -0.06
     Rossi
    -0.06
    curacy
    -0.06
    POSITIVE LOGITS
     serialVersionUID
    0.07
    ENU
    0.07
    xor
    0.06
     nonatomic
    0.06
    à¹Ģà¸Ĺ
    0.06
     jardin
    0.06
    entar
    0.06
    Multiplicity
    0.06
    enu
    0.06
    asz
    0.06
    Activations Density 0.005%

    No Known Activations