© 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. 22-LLAMASCOPE-RES-131K
    11. 3919
    Prev
    Next
    INDEX
    Explanations

    key connecting words that signify relationships in events or ideas

    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
     à¹Ĩ
    -0.09
     lately
    -0.08
    -toggler
    -0.08
     neighbors
    -0.08
     favorite
    -0.07
    urger
    -0.07
    avn
    -0.07
     neighbor
    -0.07
     colorful
    -0.07
    neighbor
    -0.07
    POSITIVE LOGITS
     UK
    0.07
     ‘
    0.06
    403
    0.06
    licence
    0.06
     programmes
    0.06
     licence
    0.06
     flavours
    0.06
     US
    0.06
     Licence
    0.06
     envis
    0.05
    Activations Density 0.001%

    No Known Activations