© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91637
    Prev
    Next
    INDEX
    Explanations

    organ

    np_max-act · gemini-2.0-flash

    terms related to organ donation and transplantation discussions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect mentions of organ donation and transplantation.

    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
    Aside
    -0.06
     hawk
    -0.06
     pří
    -0.06
    .Retrofit
    -0.06
    Exceptions
    -0.06
     TARGET
    -0.06
    /'+
    -0.06
     Ngoài
    -0.06
     고객
    -0.06
     صن
    -0.06
    POSITIVE LOGITS
    metics
    0.08
     Repo
    0.07
     resh
    0.07
    max
    0.06
    itures
    0.06
    Distance
    0.06
    erculosis
    0.06
    ricula
    0.06
    病院
    0.06
     semble
    0.06
    Activations Density 0.008%

    No Known Activations