© 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. 129745
    Prev
    Next
    INDEX
    Explanations

    themes related to romantic relationships

    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
    quo
    -0.08
    longleftrightarrow
    -0.07
    .gdx
    -0.07
    itant
    -0.07
    gle
    -0.07
    itoris
    -0.07
    elry
    -0.07
    .spi
    -0.07
    UTO
    -0.07
    bows
    -0.07
    POSITIVE LOGITS
     Lakes
    0.05
    ê
    0.05
    ieder
    0.05
    auge
    0.05
    %(
    0.05
     therein
    0.05
    åĩī
    0.05
    ëĤ¨
    0.05
     hind
    0.05
     between
    0.05
    Activations Density 0.022%

    No Known Activations