© 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. 77780
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and equality

    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
    ese
    -0.07
    owie
    -0.07
    ÅĻes
    -0.06
    è³¢
    -0.06
    rete
    -0.06
    272
    -0.06
     prive
    -0.06
    Ãłng
    -0.06
    237
    -0.06
    IRR
    -0.06
    POSITIVE LOGITS
    vasive
    0.09
    dez
    0.08
     ob
    0.07
    deaux
    0.07
     excessive
    0.07
     overposting
    0.07
    itsu
    0.07
    ëł´
    0.07
     poll
    0.07
     invasive
    0.07
    Activations Density 0.085%

    No Known Activations