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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84629
    Prev
    Next
    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “college” (and closely related college‐referencing phrases).

    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
    	im
    -0.07
    QDebug
    -0.07
     okolí
    -0.07
    Download
    -0.07
    .Gr
    -0.07
    	Server
    -0.06
     ":
    -0.06
    -Javadoc
    -0.06
    ored
    -0.06
    ije
    -0.06
    POSITIVE LOGITS
     LAS
    0.07
     Princeton
    0.07
     ens
    0.06
     bookstore
    0.06
     xếp
    0.06
    .........
    0.06
    .Transfer
    0.06
     undergrad
    0.06
    loadModel
    0.06
    resident
    0.06
    Activations Density 0.011%

    No Known Activations