© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29784
    Prev
    Next
    INDEX
    Explanations

    elements related to romance and relationship dynamics

    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
    .dds
    -0.09
    çĿĽ
    -0.09
    lero
    -0.08
    Äł
    -0.08
    à¹Īà¸Ńà¹Ħà¸Ľ
    -0.08
    abei
    -0.08
    illez
    -0.08
    .xmlbeans
    -0.07
    orrar
    -0.07
    اا
    -0.07
    POSITIVE LOGITS
    hoff
    0.07
    aka
    0.05
     psi
    0.05
     Known
    0.05
     an
    0.05
     Pro
    0.05
     every
    0.05
     only
    0.05
     faster
    0.05
    č
    0.05
    Activations Density 0.118%

    No Known Activations