© 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. 90571
    Prev
    Next
    INDEX
    Explanations

    job applications

    np_max-act · gemini-2.0-flash

    This neuron detects structured job‐posting requirement lines, i.e. the fields that list numeric specifications such as qualifications, age limits, pay scales, number of vacancies, and similar labeled parameters.

    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
    Boom
    -0.07
    -preview
    -0.07
    -plugins
    -0.06
    ال
    -0.06
     noodles
    -0.06
     Hava
    -0.06
    夫人
    -0.06
    k
    -0.06
     sync
    -0.06
    metadata
    -0.06
    POSITIVE LOGITS
    URLOPT
    0.06
     Stem
    0.06
     серед
    0.06
    Seat
    0.06
    ــــ
    0.06
    ()?;↵
    0.06
     Ches
    0.06
     pivotal
    0.06
    opr
    0.06
     najle
    0.05
    Activations Density 0.011%

    No Known Activations