© 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. 127254
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources or origins of products

    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
    elong
    -0.06
    irim
    -0.06
    ucha
    -0.06
    γÏģαμμα
    -0.06
     consumers
    -0.06
    nes
    -0.06
    ijd
    -0.06
    Exec
    -0.06
     Wilderness
    -0.06
    ederland
    -0.06
    POSITIVE LOGITS
    someone
    0.08
    sources
    0.08
     someone
    0.07
    á»Ĩ
    0.07
     sources
    0.07
     us
    0.07
     somebody
    0.07
     ÑģÑĤол
    0.07
     mesel
    0.06
     somewhere
    0.06
    Activations Density 0.022%

    No Known Activations