© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    discussions around judgment and societal perceptions regarding individuals' lifestyles or sexual orientation

    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
    builtin
    -0.08
    tout
    -0.07
     Rencontre
    -0.07
    बल
    -0.07
    ChangeEvent
    -0.06
    ellas
    -0.06
    kehr
    -0.06
    -builder
    -0.06
    bang
    -0.06
    .truth
    -0.06
    POSITIVE LOGITS
     concern
    0.10
     concerned
    0.08
     ê´Ģìĭ¬
    0.07
     Concern
    0.07
     concerns
    0.07
    ussen
    0.06
     business
    0.06
     none
    0.06
    658
    0.06
     meddling
    0.06
    Activations Density 0.033%

    No Known Activations