© 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. 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. 110384
    Prev
    Next
    INDEX
    Explanations

    Judgments/assumptions

    np_max-act · gemini-2.0-flash

    This neuron activates on language about making assumptions or judgments “based on” someone’s attributes.

    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
     Humans
    -0.07
     appreh
    -0.07
    -it
    -0.07
    Upgrade
    -0.06
    KeyId
    -0.06
     approximation
    -0.06
     Scientists
    -0.06
     fire
    -0.06
    ling
    -0.06
     Medium
    -0.06
    POSITIVE LOGITS
    宽
    0.06
    imeInterval
    0.06
    LayoutPanel
    0.06
     nhau
    0.06
    ................
    0.06
    во
    0.06
    =cut
    0.06
    ukarı
    0.06
    ographed
    0.06
    _Il
    0.06
    Activations Density 0.017%

    No Known Activations