© 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. 109286
    Prev
    Next
    INDEX
    Explanations

    cremation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of cremation and related funeral disposition terms.

    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
     의미
    -0.07
    Browse
    -0.07
     Đồng
    -0.07
    aturing
    -0.06
     '.';↵
    -0.06
    ันเป
    -0.06
    vající
    -0.06
    "),
    -0.06
     '*',
    -0.06
     pierced
    -0.06
    POSITIVE LOGITS
     crem
    0.09
    [u
    0.07
    /sm
    0.06
     Gret
    0.06
     Rem
    0.06
    OrDefault
    0.06
     Ev
    0.06
     =>'
    0.06
    rette
    0.06
    eh
    0.06
    Activations Density 0.001%

    No Known Activations