© 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. 9-LLAMASCOPE-RES-131K
    11. 95592
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to data structures and object-oriented programming concepts

    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
    roller
    -0.07
    ultz
    -0.06
    /UIKit
    -0.06
    ntity
    -0.06
     опÑĢеделен
    -0.06
     qreal
    -0.06
    êt
    -0.06
    yms
    -0.06
    elm
    -0.06
    ocate
    -0.06
    POSITIVE LOGITS
    /modules
    0.07
    855
    0.07
    krom
    0.06
    å¢ŀ
    0.06
    ensen
    0.06
    cheng
    0.06
    į°
    0.06
    aret
    0.06
     precious
    0.06
    vÄĽdom
    0.06
    Activations Density 0.023%

    No Known Activations