© 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. 126113
    Prev
    Next
    INDEX
    Explanations

    references to engagement and collaboration within organizations focused on social change

    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
    ãn
    -0.07
    ognito
    -0.07
    atrice
    -0.07
    ácil
    -0.07
    arin
    -0.06
    ût
    -0.06
     Tob
    -0.06
    tern
    -0.06
    istor
    -0.06
    zeug
    -0.06
    POSITIVE LOGITS
     communities
    0.08
     audiences
    0.08
     individuals
    0.08
     ourselves
    0.07
     partner
    0.07
     everyone
    0.07
     everybody
    0.07
    partner
    0.06
    /DD
    0.06
     others
    0.06
    Activations Density 0.031%

    No Known Activations