© 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. 56156
    Prev
    Next
    INDEX
    Explanations

    code constructs related to class inheritance and implementation

    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
    lisi
    -0.09
     lô
    -0.09
    eÄį
    -0.08
    ép
    -0.08
    htag
    -0.07
    mÃŃ
    -0.07
    âĢŀTo
    -0.07
    ethereum
    -0.07
    DataManager
    -0.07
    оваÑĢ
    -0.07
    POSITIVE LOGITS
    ans
    0.06
     PAC
    0.05
    ANS
    0.05
    oen
    0.05
    ero
    0.05
    36
    0.05
     Barg
    0.05
     class
    0.05
    427
    0.05
    quiring
    0.05
    Activations Density 0.002%

    No Known Activations