© 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. 125639
    Prev
    Next
    INDEX
    Explanations

    expressions of guidance and support in personal development

    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
    avian
    -0.07
    afx
    -0.07
    ê³µ
    -0.07
    Äįen
    -0.06
    kir
    -0.06
    Mess
    -0.06
     Flint
    -0.06
    akat
    -0.06
     mã
    -0.06
    anni
    -0.06
    POSITIVE LOGITS
     whenever
    0.07
     Pride
    0.07
     amb
    0.07
    ãĥ¼ãĥĦ
    0.06
    cia
    0.06
     اÙĦأد
    0.06
    mot
    0.06
    ",__
    0.06
    opus
    0.06
    iani
    0.06
    Activations Density 0.046%

    No Known Activations