© 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. 22-LLAMASCOPE-RES-131K
    11. 3633
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to class implementation in Java

    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
    ature
    -0.08
     Ko
    -0.06
    umat
    -0.06
     ArgumentNullException
    -0.06
    UMB
    -0.06
    âħ
    -0.06
    andy
    -0.06
    atures
    -0.06
    pus
    -0.06
     recall
    -0.06
    POSITIVE LOGITS
     Comparable
    0.12
    Comparable
    0.12
     Clone
    0.10
     Serializable
    0.10
    Clone
    0.09
    Serializable
    0.09
     comparable
    0.09
     Parcelable
    0.09
    .Clone
    0.07
    .clone
    0.07
    Activations Density 0.003%

    No Known Activations