© 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. 73722
    Prev
    Next
    INDEX
    Explanations

    og

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific individuals—proper names of people (especially victims or targets) in news reports of political violence or investigations.

    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
     Laravel
    -0.06
     LAN
    -0.06
    地区
    -0.06
     Fem
    -0.06
     arriv
    -0.06
     raid
    -0.06
     gerçekleş
    -0.06
     reading
    -0.06
     organisers
    -0.06
    -using
    -0.06
    POSITIVE LOGITS
    (fragment
    0.07
     recal
    0.06
    Ada
    0.06
     systemic
    0.06
     pai
    0.06
     fondo
    0.06
     대표
    0.06
    [url
    0.06
     pik
    0.06
    Rew
    0.06
    Activations Density 0.007%

    No Known Activations