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. 40436
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron is detecting the opening double‐quote that begins a string literal.

    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
     اختص
    -0.07
    sın
    -0.07
     рекомен
    -0.06
    ypad
    -0.06
    رفت
    -0.06
    lichen
    -0.06
    บรร
    -0.06
    &oacute
    -0.06
     француз
    -0.06
    _CUBE
    -0.06
    POSITIVE LOGITS
    ROT
    0.06
     reserved
    0.06
    \n
    0.06
     český
    0.06
     코로나
    0.06
     Conference
    0.06
    ?”
    0.06
     decentralized
    0.06
    >#
    0.06
     multim
    0.06
    Activations Density 0.001%

    No Known Activations