Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109553
    Prev
    Next
    INDEX
    Explanations

    applicant

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “Applicant” (and its inflected forms) in formal application or patent-style texts.

    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
    gii
    -0.07
     ні
    -0.06
     Buttons
    -0.06
    taxonomy
    -0.06
    虎
    -0.06
    厚
    -0.06
     ضد
    -0.06
    Defense
    -0.06
     činnosti
    -0.06
    prt
    -0.06
    POSITIVE LOGITS
    -month
    0.08
     olduğ
    0.07
     straight
    0.07
    invest
    0.07
    caller
    0.07
    -get
    0.07
    rawer
    0.07
    ?),
    0.07
    alist
    0.07
     applicants
    0.07
    Activations Density 0.003%

    No Known Activations