© 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. 7589
    Prev
    Next
    INDEX
    Explanations

    Progress over time

    np_max-act · gemini-2.0-flash

    This neuron activates on short procedural or rule statements (e.g. phrasing that specifies what is or isn’t allowed).

    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
     ambassador
    -0.07
     obtaining
    -0.06
     Rib
    -0.06
    Disc
    -0.06
     различ
    -0.06
     transporter
    -0.06
     Father
    -0.06
     granny
    -0.06
     Roo
    -0.06
    toContain
    -0.06
    POSITIVE LOGITS
     bookings
    0.06
     بوابة
    0.06
    CRT
    0.06
    *****
↵
    0.06
     лік
    0.06
    .surname
    0.06
    -used
    0.06
     �
    0.06
    nika
    0.06
    ?>;↵
    0.06
    Activations Density 0.068%

    No Known Activations