© 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. 15-LLAMASCOPE-RES-131K
    11. 104417
    Prev
    Next
    INDEX
    Explanations

    instances of contact information and user engagement prompts

    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
    viÄį
    -0.07
    баÑģ
    -0.07
    ýš
    -0.07
    structuring
    -0.07
     olsa
    -0.07
    vem
    -0.07
    å¹²
    -0.07
    shaw
    -0.07
    oro
    -0.07
     daunting
    -0.07
    POSITIVE LOGITS
     availability
    0.08
    coe
    0.06
    coon
    0.06
     latest
    0.06
     Latest
    0.06
    Availability
    0.06
     available
    0.06
     Availability
    0.06
     pron
    0.06
     posts
    0.06
    Activations Density 0.063%

    No Known Activations