© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57811
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron detects chemical terms containing “fluor” (especially as part of trifluoromethyl-type fragments).

    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
     Beauty
    -0.07
     �
    -0.06
    aktu
    -0.06
    	begin
    -0.06
     Reg
    -0.06
     Goddess
    -0.06
    elidir
    -0.06
     نموده
    -0.06
    ily
    -0.06
     브라
    -0.06
    POSITIVE LOGITS
    .Actor
    0.07
    нер
    0.07
    -vers
    0.06
    寒
    0.06
     uv
    0.06
     assessments
    0.06
    彦
    0.06
    .converter
    0.06
     Scholar
    0.06
    059
    0.06
    Activations Density 0.002%

    No Known Activations