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

    Neuronpedia

    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. 78894
    Prev
    Next
    INDEX
    Explanations

    terms related to romantic relationships and breakups

    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
    wart
    -0.07
    upa
    -0.07
    enu
    -0.07
    Äįer
    -0.07
    entes
    -0.07
    semb
    -0.06
    èn
    -0.06
     Wahl
    -0.06
    alis
    -0.06
     اÙĦسÙĦاÙħ
    -0.06
    POSITIVE LOGITS
    /div
    0.09
     Ler
    0.07
     khá»ıi
    0.07
     kola
    0.06
    AMESPACE
    0.06
    Breaking
    0.06
    nore
    0.06
     breaking
    0.06
    ież
    0.06
    indre
    0.06
    Activations Density 0.010%

    No Known Activations