© 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. 15-LLAMASCOPE-RES-131K
    11. 88945
    Prev
    Next
    INDEX
    Explanations

    references to organizations involved in clean water initiatives

    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
     mouth
    -0.07
    evin
    -0.06
    angl
    -0.06
    idl
    -0.06
    viar
    -0.06
     mouths
    -0.06
    -mouth
    -0.06
     repeated
    -0.05
     seventh
    -0.05
    blink
    -0.05
    POSITIVE LOGITS
    αÏģά
    0.08
    åIJĦ
    0.08
    ÑĢабаÑĤ
    0.07
    NCY
    0.07
    WithMany
    0.07
    arro
    0.07
    /member
    0.07
    ãĥ³ãĤ¹
    0.06
    dock
    0.06
     Hindered
    0.06
    Activations Density 0.025%

    No Known Activations