© 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. 119813
    Prev
    Next
    INDEX
    Explanations

    references to the city of Rome

    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
    mente
    -0.08
    ria
    -0.08
    ment
    -0.08
    ship
    -0.07
    rost
    -0.07
    upply
    -0.06
     обол
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    rin
    -0.06
     footh
    -0.06
    POSITIVE LOGITS
    panion
    0.08
    ivec
    0.08
    lesc
    0.07
    bero
    0.07
    Ø®ÛĮ
    0.07
    agna
    0.07
     numer
    0.06
     ведÑĮ
    0.06
    antically
    0.06
    cratch
    0.06
    Activations Density 0.014%

    No Known Activations