© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89694
    Prev
    Next
    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of conserved quantum‐number terms—especially “baryon number” and “lepton number.”

    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
     mosquito
    -0.07
    네
    -0.07
     fax
    -0.07
    choice
    -0.06
     cancellation
    -0.06
     Cel
    -0.06
    (inputStream
    -0.06
     counterfeit
    -0.06
    ois
    -0.06
    .End
    -0.06
    POSITIVE LOGITS
     стен
    0.07
     městě
    0.06
    ::{↵
    0.06
     allowable
    0.06
     uveden
    0.06
     concentrating
    0.06
     cheesy
    0.06
     normalized
    0.06
    !("{
    0.06
     вина
    0.06
    Activations Density 0.001%

    No Known Activations