© 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. 9-LLAMASCOPE-RES-131K
    11. 95374
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and codes

    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
    uda
    -0.07
    erts
    -0.06
    ara
    -0.06
    age
    -0.06
    ect
    -0.05
     complexes
    -0.05
    ut
    -0.05
    st
    -0.05
    468
    -0.05
    aud
    -0.05
    POSITIVE LOGITS
     bordel
    0.07
    íĥĦ
    0.07
    ãĢģãĢģ
    0.07
    ¶Į
    0.07
    SCII
    0.07
    iá»ĩn
    0.07
     bach
    0.07
    ï¼
    0.07
     hete
    0.07
    rych
    0.07
    Activations Density 0.001%

    No Known Activations