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

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125688
    Prev
    Next
    INDEX
    Explanations

    code-related terms or functions associated with state management and transitions

    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
    ombine
    -0.07
    enler
    -0.07
    atorio
    -0.07
    ;element
    -0.07
    owski
    -0.07
    à¸ļà¸ļ
    -0.07
    dal
    -0.07
    ¡
    -0.07
    ertino
    -0.07
    xdb
    -0.07
    POSITIVE LOGITS
    ãĤ¯ãĥĪ
    0.07
    rew
    0.06
    eko
    0.06
    ãĥĭãĤ¢
    0.06
     Emil
    0.05
    ben
    0.05
    guard
    0.05
    iant
    0.05
    TypeDef
    0.05
    berapa
    0.05
    Activations Density 0.031%

    No Known Activations