© 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. 54190
    Prev
    Next
    INDEX
    Explanations

    Scientific procedures

    np_max-act · gemini-2.0-flash

    This neuron activates on procedural action verbs (e.g., “added,” “stirred,” “heated,” “cooled”) describing steps in a chemistry protocol.

    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
     paris
    -0.07
    fried
    -0.06
    _logs
    -0.06
     μαζί
    -0.06
     PDT
    -0.06
    LOG
    -0.06
    URITY
    -0.06
    INARY
    -0.06
    Probably
    -0.05
    (position
    -0.05
    POSITIVE LOGITS
    .isFile
    0.07
    参加
    0.07
    -guid
    0.07
     inhibition
    0.06
    اجات
    0.06
    onis
    0.06
    .Resource
    0.06
    <Form
    0.06
     відповід
    0.06
    ection
    0.06
    Activations Density 0.007%

    No Known Activations