© 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. 110184
    Prev
    Next
    INDEX
    Explanations

    Resumes

    np_max-act · gemini-2.0-flash

    The neuron fires on directives to “include” specific information (e.g. “Include … on a resume”).

    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
    .request
    -0.06
    undo
    -0.06
    _slices
    -0.06
    arrass
    -0.06
    afen
    -0.06
    пис
    -0.06
     contend
    -0.06
    acement
    -0.06
     hôn
    -0.06
     w
    -0.06
    POSITIVE LOGITS
     Mao
    0.07
     fluent
    0.07
    İK
    0.06
     gauche
    0.06
     Saskatchewan
    0.06
     dormant
    0.06
    =t
    0.06
     Wear
    0.06
     chuyến
    0.06
     Sq
    0.06
    Activations Density 0.045%

    No Known Activations