© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129805
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on specialized polymer/material‐science adjectives and modifiers (e.g. amphiphilic, hydrophilic, biodegradable) describing chemical or structural features of materials.

    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
     real
    -0.06
     troubling
    -0.06
     pre
    -0.06
    兰
    -0.06
     Knowledge
    -0.06
     خلف
    -0.06
     能
    -0.06
     growing
    -0.06
     legitimate
    -0.06
    NC
    -0.06
    POSITIVE LOGITS
     запас
    0.07
     praying
    0.07
    ">@
    0.06
     sayf
    0.06
    (formData
    0.06
     reverted
    0.06
    .static
    0.06
     参数
    0.06
    افر
    0.06
    ioxid
    0.06
    Activations Density 0.121%

    No Known Activations