© 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. 83387
    Prev
    Next
    INDEX
    Explanations

    references to offshore activities and locations

    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
    asso
    -0.09
    soever
    -0.07
    itesse
    -0.07
    ä¸ĸ
    -0.07
    makers
    -0.07
    ãĥ¼ãĥį
    -0.07
    sei
    -0.07
    asic
    -0.07
    ottes
    -0.07
     Bros
    -0.06
    POSITIVE LOGITS
    /off
    0.11
    /on
    0.10
    /at
    0.07
    abay
    0.07
    /local
    0.07
    (off
    0.07
    -bound
    0.07
     breeze
    0.06
    /down
    0.06
    Ìī
    0.06
    Activations Density 0.002%

    No Known Activations