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. 125693
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    This neuron detects legal case citations, specifically the volume, reporter abbreviation, and page number strings (e.g. “809 S.W.2d 188”).

    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
    χαν
    -0.07
     nhiễ
    -0.06
    >#
    -0.06
    如下
    -0.06
     Execute
    -0.06
    =<?=$
    -0.06
     đàn
    -0.06
    ΕΙ
    -0.06
    .checkNotNull
    -0.06
    \Image
    -0.06
    POSITIVE LOGITS
     Comment
    0.07
    urers
    0.07
    τα
    0.06
     impose
    0.06
     uptake
    0.06
    (java
    0.06
    ration
    0.06
     fittings
    0.06
     complexities
    0.06
    [random
    0.06
    Activations Density 0.007%

    No Known Activations