© 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. 74788
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    applications of specific chemical compounds in various industries.

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

    This neuron fires on mentions of the chemical‐industry context (e.g. phrases like “in the chemical industry”).

    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
    âk
    -0.08
     watchdog
    -0.06
     довольно
    -0.06
    !]
    -0.06
    好き
    -0.06
    flater
    -0.06
     เก
    -0.06
    .Act
    -0.06
    uncan
    -0.06
     intend
    -0.06
    POSITIVE LOGITS
     Υ
    0.07
    ضی
    0.06
    验
    0.06
    groundColor
    0.06
    <Field
    0.06
     Mandatory
    0.06
     Nuggets
    0.06
     arrival
    0.06
     strtok
    0.06
    enzie
    0.06
    Activations Density 0.016%

    No Known Activations