© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59442
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects summary‐style headings (e.g. “Summary,” “Description”) that introduce recap sections.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    STEP
    -0.07
    ]):
↵
    -0.06
    都市
    -0.06
    	net
    -0.06
    Step
    -0.06
    ,\↵
    -0.06
    Clock
    -0.06
    Returns
    -0.06
    影響
    -0.06
     babys
    -0.05
    POSITIVE LOGITS
     ballistic
    0.07
     zx
    0.07
    ोकर
    0.07
     Liv
    0.07
    лой
    0.06
     Disposable
    0.06
     mọi
    0.06
    /footer
    0.06
     Dominic
    0.06
    /models
    0.06
    Activations Density 0.023%

    No Known Activations