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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27072
    Prev
    Next
    INDEX
    Explanations

    Stat

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric citation details (e.g. statute and reporter volume/page numbers) in legal references.

    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
     welche
    -0.07
    闲
    -0.07
    �
    -0.07
    coholic
    -0.07
     pods
    -0.06
     dva
    -0.06
     acupuncture
    -0.06
    C
    -0.06
    .:.:.
    -0.06
    dept
    -0.06
    POSITIVE LOGITS
     David
    0.07
     ITER
    0.07
     Bradford
    0.06
     Doctors
    0.06
     stat
    0.06
     conditioned
    0.06
    .Place
    0.06
    atts
    0.06
    мер
    0.06
    .Stat
    0.06
    Activations Density 0.000%

    No Known Activations