© 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. 61469
    Prev
    Next
    INDEX
    Explanations

    references to boycotts and protests

    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
    Disposition
    -0.07
     lạ
    -0.06
    ermann
    -0.06
    emes
    -0.06
    lements
    -0.06
     Exped
    -0.06
    гÑĥ
    -0.06
    teÅŁ
    -0.06
    Ùħت
    -0.06
    iane
    -0.06
    POSITIVE LOGITS
     protest
    0.11
     protesting
    0.10
     refusal
    0.09
     demanding
    0.08
     refuse
    0.08
     Protest
    0.08
     refusing
    0.08
    usk
    0.08
     boyc
    0.07
     Princip
    0.07
    Activations Density 0.024%

    No Known Activations