© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92641
    Prev
    Next
    INDEX
    Explanations

    Officials

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the word “Officials,” especially when used as the lead term attributing a statement to authorities.

    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
    áy
    -0.07
     edge
    -0.07
     deutschland
    -0.06
     spr
    -0.06
    .enter
    -0.06
    	bar
    -0.06
    -energy
    -0.06
     vap
    -0.06
    ¥
    -0.06
    +p
    -0.06
    POSITIVE LOGITS
     officials
    0.13
     Officials
    0.13
    Officials
    0.10
     official
    0.09
     Official
    0.09
    ؤ
    0.08
     UIButton
    0.07
    1
    0.07
     scoff
    0.07
     coal
    0.07
    Activations Density 0.006%

    No Known Activations