© 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. 17-LLAMASCOPE-RES-131K
    11. 75560
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to method calls and object properties

    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
    æī¹
    -0.07
    eyen
    -0.07
    reserved
    -0.07
    ock
    -0.06
    .enums
    -0.06
    akra
    -0.06
    Reserved
    -0.06
     Cong
    -0.06
    pal
    -0.06
     reserved
    -0.06
    POSITIVE LOGITS
    illions
    0.07
    .writeObject
    0.07
     objeto
    0.07
    OBJ
    0.07
     jobject
    0.07
     Obj
    0.07
    obj
    0.07
    assertInstanceOf
    0.07
    <typeof
    0.06
     object
    0.06
    Activations Density 0.045%

    No Known Activations