© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56866
    Prev
    Next
    INDEX
    Explanations

    eral

    np_max-act · gemini-2.0-flash

    The neuron detects the substring “liberal” (and its morphological variants) anywhere it appears.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Casey
    -0.07
     Watch
    -0.07
     Byrne
    -0.07
     Ernst
    -0.06
    Scott
    -0.06
    Danger
    -0.06
     место
    -0.06
    foo
    -0.06
     Однак
    -0.06
    seniz
    -0.06
    POSITIVE LOGITS
     Liberal
    0.12
     liberal
    0.11
    lap
    0.09
     liber
    0.09
    bol
    0.08
    igmat
    0.08
     Liberals
    0.08
    RAM
    0.08
     개
    0.07
     Lib
    0.07
    Activations Density 0.004%

    No Known Activations