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. 86029
    Prev
    Next
    INDEX
    Explanations

    Common sentence structure

    np_max-act · gemini-2.0-flash

    The neuron fires on subjective evaluation or summary statements—especially “Overall,” and the adjoining judgmental or descriptive language that wraps up a review.

    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
    (rand
    -0.07
    ervals
    -0.06
    ている
    -0.06
    град
    -0.06
     firsthand
    -0.06
    pipeline
    -0.06
     outlines
    -0.06
     equip
    -0.06
    .birth
    -0.06
     |\
    -0.06
    POSITIVE LOGITS
     skyline
    0.08
     dni
    0.06
     možné
    0.06
    abelle
    0.06
     vowed
    0.06
     yönetimi
    0.06
    �
    0.06
     println
    0.06
     approximate
    0.06
     tournaments
    0.06
    Activations Density 0.059%

    No Known Activations