© 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. 58235
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron fires primarily on floating‐point numeric literals (decimal numbers, e.g. “-3.912109375”).

    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
    [tmp
    -0.06
    atab
    -0.06
     जनत
    -0.06
     "+
    -0.06
    ğın
    -0.06
    aversal
    -0.06
    чно
    -0.06
     chained
    -0.06
    PickerController
    -0.06
    otic
    -0.06
    POSITIVE LOGITS
     Dealers
    0.07
    -dismiss
    0.06
    Optional
    0.06
    going
    0.06
     complying
    0.06
     частини
    0.06
    -lib
    0.06
     Pháp
    0.06
     سنوات
    0.06
    ając
    0.06
    Activations Density 0.003%

    No Known Activations