© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91298
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on decimal numeric values and measurements (e.g. statistical values, concentrations, and precise quantitative data).

    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
     </
    -0.07
     pretending
    -0.07
    Desktop
    -0.06
    ajor
    -0.06
    CR
    -0.06
    ());
    ↵
    -0.06
    four
    -0.06
    елов
    -0.06
     pretended
    -0.06
     Claire
    -0.06
    POSITIVE LOGITS
    سان
    0.07
     seizures
    0.06
     다운
    0.06
    려고
    0.06
     Unlock
    0.06
     pob
    0.06
     불
    0.06
     душ
    0.06
    hd
    0.06
    でしょう
    0.06
    Activations Density 0.166%

    No Known Activations