© 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. 5-LLAMASCOPE-RES-131K
    11. 125758
    Prev
    Next
    INDEX
    Explanations

    references to bananas

    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
     offs
    -0.07
    reck
    -0.07
    ests
    -0.07
    tur
    -0.06
    oston
    -0.06
    -feedback
    -0.06
    unate
    -0.06
    dra
    -0.06
    rah
    -0.06
    ald
    -0.06
    POSITIVE LOGITS
    embros
    0.07
    iglia
    0.06
    apolis
    0.06
    arez
    0.06
    -caret
    0.06
     Lover
    0.06
    arend
    0.06
    esium
    0.06
    alam
    0.06
    ipro
    0.06
    Activations Density 0.001%

    No Known Activations