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. 130205
    Prev
    Next
    INDEX
    Explanations

    001

    np_max-act · gemini-2.0-flash

    This neuron detects in-text citation markers (bracketed reference tags like “[@…ref…]”).

    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
     curing
    -0.06
     desarrollo
    -0.06
    <Service
    -0.06
    ражд
    -0.06
    RAY
    -0.06
    965
    -0.06
    (utils
    -0.06
     pref
    -0.06
    reibung
    -0.05
     صورت
    -0.05
    POSITIVE LOGITS
    ifix
    0.07
     hg
    0.07
     Chop
    0.07
     Benchmark
    0.07
     dbo
    0.07
    ='',
    0.06
    �
    0.06
    _every
    0.06
    orgt
    0.06
     timestamps
    0.06
    Activations Density 0.002%

    No Known Activations