© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120581
    Prev
    Next
    INDEX
    Explanations

    expressions of discontent or criticism related to political figures

    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
    iring
    -0.07
    abee
    -0.07
    inder
    -0.07
    agini
    -0.07
    occo
    -0.07
    291
    -0.06
    anian
    -0.06
    ynes
    -0.06
    anel
    -0.06
    hrad
    -0.06
    POSITIVE LOGITS
     saying
    0.08
     meaning
    0.07
    meaning
    0.07
    érc
    0.07
    STACK
    0.06
     Saying
    0.06
    leo
    0.06
     Ú¯ÙĪ
    0.06
    Ïĥκ
    0.06
     statement
    0.06
    Activations Density 0.063%

    No Known Activations