© 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. 57081
    Prev
    Next
    INDEX
    Explanations

    PI

    np_max-act · gemini-2.0-flash

    legal terms and concepts related to criminal charges and court proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on uncommon or “out-of-vocabulary” tokens—e.g. acronyms, chemical names, or rare capitalized/abnormal strings.

    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
     Ц
    -0.07
     staple
    -0.06
     BEEN
    -0.06
     inté
    -0.06
     recep
    -0.06
    daily
    -0.06
     cít
    -0.06
    vail
    -0.06
     bitte
    -0.06
    、私
    -0.06
    POSITIVE LOGITS
     iconName
    0.07
     Держав
    0.07
    'e
    0.07
    isVisible
    0.07
    _measure
    0.06
    _cut
    0.06
     </
    0.06
     Bek
    0.06
     esos
    0.06
     genus
    0.06
    Activations Density 0.306%

    No Known Activations