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

    Neuronpedia

    APICircuit 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. 40665
    Prev
    Next
    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash

    The neuron flags numerical performance statistics and superlative metrics (e.g. rankings, “best,” “highest,” and related numbers) in athlete biographies.

    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
    	t
    -0.07
     نظر
    -0.07
    .Option
    -0.07
    <KeyValuePair
    -0.06
     stumbled
    -0.06
     employer
    -0.06
     समर
    -0.06
     fertilizer
    -0.06
    _INV
    -0.06
    (rotation
    -0.06
    POSITIVE LOGITS
     où
    0.07
    renal
    0.07
    rej
    0.06
     Macy
    0.06
    ANN
    0.06
     corresponds
    0.06
    ække
    0.06
    createClass
    0.06
    623
    0.06
    signed
    0.06
    Activations Density 0.008%

    No Known Activations