© 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. 91127
    Prev
    Next
    INDEX
    Explanations

    88

    np_max-act · gemini-2.0-flash

    The neuron detects capitalized technology‐related domain words (like “Software,” “Data,” “Cyber,” “IT”) that occur at the start of job titles.

    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
     plagued
    -0.07
    EMAIL
    -0.07
    Unified
    -0.06
     (::
    -0.06
    236
    -0.06
    -Length
    -0.06
    SORT
    -0.06
     autistic
    -0.06
     Canter
    -0.06
    Atlas
    -0.06
    POSITIVE LOGITS
    (instruction
    0.06
    INS
    0.06
    	left
    0.06
     Dove
    0.06
    cone
    0.06
    .None
    0.06
    "go
    0.05
     garlic
    0.05
     tqdm
    0.05
    NameValuePair
    0.05
    Activations Density 0.098%

    No Known Activations