© 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. 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. 58184
    Prev
    Next
    INDEX
    Explanations

    ifer

    np_max-act · gemini-2.0-flash

    The neuron selectively detects occurrences of the term “proliferative” (and its embedded substring “proliferativ”) in medical or scientific phrasing.

    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
    />";↵
    -0.06
    :↵↵↵↵↵↵
    -0.06
    ноп
    -0.06
    (found
    -0.06
     smashing
    -0.06
    (back
    -0.06
    Oregon
    -0.06
    .masksToBounds
    -0.06
     záb
    -0.06
    	↵	↵
    -0.05
    POSITIVE LOGITS
    RE
    0.07
     lover
    0.07
    adr
    0.07
    žitě
    0.07
     Genre
    0.07
     LIFE
    0.07
    ues
    0.07
    ICK
    0.07
     AGE
    0.07
    bury
    0.07
    Activations Density 0.001%

    No Known Activations