© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3722
    Prev
    Next
    INDEX
    Explanations

    references to customer service issues and theft in a retail context

    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
    compound
    -0.07
     æĬķ
    -0.07
     clap
    -0.06
     Political
    -0.06
    ndata
    -0.06
     compound
    -0.06
     political
    -0.06
    ñana
    -0.06
    ccione
    -0.06
    çŃĭ
    -0.06
    POSITIVE LOGITS
     theft
    0.07
    .codes
    0.07
    gio
    0.07
     department
    0.07
     shop
    0.07
     checkout
    0.07
    /item
    0.06
     outlet
    0.06
     Theft
    0.06
     Item
    0.06
    Activations Density 0.006%

    No Known Activations