© 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. 58121
    Prev
    Next
    INDEX
    Explanations

    advice and instructions

    np_max-act · gemini-2.0-flash

    The neuron activates on structured subsection headings, especially the phrases “Case Study” and “Best Practices.”

    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
     switches
    -0.06
    ､
    -0.06
    234
    -0.06
    _l
    -0.06
     compressed
    -0.06
    _t
    -0.06
    display
    -0.06
     Βασ
    -0.06
     Switch
    -0.06
    (ptr
    -0.06
    POSITIVE LOGITS
     جع
    0.08
    -screen
    0.07
     Bowl
    0.06
     Cement
    0.06
    знача
    0.06
     ");
↵
    0.06
    艾
    0.06
    érer
    0.06
     afr
    0.06
    보고
    0.06
    Activations Density 0.064%

    No Known Activations