© 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. 125272
    Prev
    Next
    INDEX
    Explanations

    journalist

    np_max-act · gemini-2.0-flash

    The neuron activates on biographical mentions of someone’s profession as a journalist (and closely related reporting roles).

    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
    prite
    -0.07
    wor
    -0.07
     slo
    -0.06
     Sco
    -0.06
     vů
    -0.06
    IN
    -0.06
     Beds
    -0.06
    ibe
    -0.06
     lineback
    -0.06
     exter
    -0.06
    POSITIVE LOGITS
     journalist
    0.14
     journalists
    0.11
     journalism
    0.11
     Journalism
    0.11
     journalistic
    0.09
     reporting
    0.08
     アイ
    0.07
     judiciary
    0.07
     Essay
    0.07
    zM
    0.07
    Activations Density 0.005%

    No Known Activations