© 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. 86101
    Prev
    Next
    INDEX
    Explanations

    royal titles and notable historical figures or places

    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
    sgi
    -0.07
    emachine
    -0.07
    azzi
    -0.06
    acf
    -0.06
    HQ
    -0.06
    ilio
    -0.06
     deutschland
    -0.06
    wf
    -0.06
    arry
    -0.06
    draul
    -0.06
    POSITIVE LOGITS
    ensis
    0.10
     wed
    0.07
    970
    0.07
    gnore
    0.07
    gre
    0.07
    олÑİ
    0.07
     ฿
    0.06
    ský
    0.06
    ÑĤал
    0.06
    ompiler
    0.06
    Activations Density 0.008%

    No Known Activations