© 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. 56231
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron fires on the standalone version number “2” (e.g. in “Version 2.0”) in license and header blocks.

    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
     Anchor
    -0.06
     qry
    -0.06
    136
    -0.06
    'utilisation
    -0.06
     SL
    -0.06
     pins
    -0.06
     XmlNode
    -0.06
     Glow
    -0.06
     udp
    -0.06
     regs
    -0.06
    POSITIVE LOGITS
    auté
    0.07
    onic
    0.07
     Own
    0.07
    (begin
    0.07
     sitio
    0.07
    .Spring
    0.07
    	opt
    0.07
     спе
    0.07
    도록
    0.07
    .union
    0.06
    Activations Density 0.001%

    No Known Activations