© 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. 44587
    Prev
    Next
    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive and does not respond to any tokens.

    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
     землю
    -0.07
     розум
    -0.07
     pisc
    -0.07
    	M
    -0.06
     забезпечення
    -0.06
     bajo
    -0.06
     mechan
    -0.06
     quantidade
    -0.06
     mes
    -0.06
     resposta
    -0.06
    POSITIVE LOGITS
    	glVertex
    0.06
    (Calendar
    0.06
    IEnumerator
    0.06
    توبر
    0.06
    ??
    0.06
     TreeMap
    0.06
    \HttpFoundation
    0.06
    !,↵
    0.06
    (quantity
    0.06
    )."
    0.06
    Activations Density 0.023%

    No Known Activations