© 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. 9-LLAMASCOPE-RES-131K
    11. 95741
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and relationships among individuals

    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
    ampie
    -0.07
    оÑĤе
    -0.07
    otor
    -0.07
    podob
    -0.07
    иÑĨин
    -0.07
    ithe
    -0.07
    ummings
    -0.07
    /REC
    -0.07
    Formats
    -0.07
    ©
    -0.07
    POSITIVE LOGITS
    èĪį
    0.06
    rie
    0.06
    iol
    0.06
     Tiffany
    0.06
    371
    0.05
     coun
    0.05
     Liberties
    0.05
     Woodward
    0.05
     Tip
    0.05
     Becker
    0.05
    Activations Density 0.029%

    No Known Activations