© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126405
    Prev
    Next
    INDEX
    Explanations

    chemical filtration/separation

    np_max-act · gemini-2.0-flash

    The neuron is attuned to numeric measurement tokens—especially decimal numbers and quantities—in the chemical procedure text.

    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
     dismiss
    -0.06
    itelist
    -0.06
    636
    -0.06
    imator
    -0.06
     binaries
    -0.06
    ﻟ
    -0.06
    ipe
    -0.05
    InputStream
    -0.05
    ænd
    -0.05
    .Spec
    -0.05
    POSITIVE LOGITS
     America
    0.07
    患者
    0.06
    sword
    0.06
    ancellationToken
    0.06
     εμφ
    0.06
     sigh
    0.06
     akıl
    0.06
     ///</
    0.06
     Cavs
    0.06
     Chloe
    0.06
    Activations Density 0.011%

    No Known Activations