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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 128807
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly those associated with Parcelable 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
    å¾ģ
    -0.07
    ç§ģãģ®
    -0.07
     prive
    -0.07
     Ñĥв
    -0.07
     Mask
    -0.06
    (EC
    -0.06
    lobs
    -0.06
    uent
    -0.06
    âĻ¡
    -0.06
    lobals
    -0.06
    POSITIVE LOGITS
    .readInt
    0.07
    rub
    0.07
     rub
    0.07
    avenport
    0.06
    .Parcel
    0.06
    tach
    0.06
     rubbed
    0.06
     Cutter
    0.06
    andel
    0.06
     tang
    0.06
    Activations Density 0.003%

    No Known Activations