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. 130572
    Prev
    Next
    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash

    Neuron 4 is detecting date‐related field labels (e.g. “Date Collected,” “Date Received,” “Date Reported,” etc.) in the form.

    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
     text
    -0.07
    IBLE
    -0.06
     вже
    -0.06
    .collider
    -0.06
    jím
    -0.06
     Aging
    -0.06
    ()=>
    -0.06
    =""/>↵
    -0.06
    SW
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     nog
    0.07
     aluno
    0.07
     pří
    0.07
     QIcon
    0.06
     Plum
    0.06
    fdf
    0.06
     Draws
    0.06
     직접
    0.06
     příč
    0.06
     تور
    0.06
    Activations Density 0.002%

    No Known Activations