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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 116987
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and related phrases suggesting contact or communication

    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
    виÑĩ
    -0.08
     Brend
    -0.06
    ems
    -0.06
    ân
    -0.06
    uts
    -0.06
    otec
    -0.06
    esc
    -0.06
    ovice
    -0.06
    สำà¹Ģร
    -0.06
    ena
    -0.06
    POSITIVE LOGITS
    /text
    0.09
    /email
    0.08
     toll
    0.08
    oused
    0.07
     âĢª
    0.07
     thoại
    0.07
    .ACTION
    0.07
    /***/
    0.07
     attention
    0.07
    @nate
    0.06
    Activations Density 0.006%

    No Known Activations