© 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 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. 88481
    Prev
    Next
    INDEX
    Explanations

    instances of the word "like" in various contexts

    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
    orno
    -0.06
    åIJįçĦ¡ãģĹ
    -0.06
    uti
    -0.06
     åķ
    -0.06
    gid
    -0.06
     ÑĤÑĢÑĥдов
    -0.06
    ckt
    -0.06
    à¥įयम
    -0.06
    aÄŁ
    -0.06
     daÃŁ
    -0.06
    POSITIVE LOGITS
    oping
    0.06
    reur
    0.06
    _mC
    0.06
    ili
    0.06
    _mE
    0.06
    _mB
    0.06
     naï
    0.06
     Mot
    0.06
     podium
    0.06
     Plan
    0.06
    Activations Density 0.000%

    No Known Activations