© 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. 106233
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or entities

    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
    alette
    -0.07
    ayah
    -0.07
    BERT
    -0.07
    ùa
    -0.07
     onDataChange
    -0.07
    roupon
    -0.07
     вик
    -0.07
    غاÙĨ
    -0.07
    ække
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
    velt
    0.09
     his
    0.07
     inside
    0.06
    vek
    0.06
     Savannah
    0.06
     hay
    0.06
     se
    0.06
    omba
    0.05
    loy
    0.05
     rel
    0.05
    Activations Density 0.001%

    No Known Activations