© 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. 93402
    Prev
    Next
    INDEX
    Explanations

    references to new experiences or items

    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
     Tester
    -0.08
    íĮħ
    -0.07
    %C
    -0.07
    :UIAlert
    -0.07
    å¡ļ
    -0.07
    áºŃp
    -0.06
     aforementioned
    -0.06
    ocities
    -0.06
     unavoid
    -0.06
    对äºİ
    -0.06
    POSITIVE LOGITS
    allen
    0.06
    xing
    0.06
    æ®ĭ
    0.06
    AXB
    0.06
    ensburg
    0.06
     slices
    0.06
    eba
    0.06
    åĸĦ
    0.06
    äs
    0.06
     Scandin
    0.06
    Activations Density 0.000%

    No Known Activations