© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 921
    Prev
    Next
    INDEX
    Explanations

    domain endings

    np_max-act · gemini-2.0-flash

    This neuron detects parts of web URLs, especially domain names and top-level domains (e.g., “.com,” “.net,” etc.).

    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
    해야
    -0.06
     cooled
    -0.06
    Than
    -0.06
    readcrumbs
    -0.06
    ane
    -0.06
     Democr
    -0.06
    lied
    -0.06
     seniors
    -0.06
     weld
    -0.06
    anes
    -0.06
    POSITIVE LOGITS
     amt
    0.06
    ORIZATION
    0.06
     invest
    0.06
     FORM
    0.06
    gist
    0.06
    ость
    0.06
    айт
    0.06
                          ↵
    0.06
     Gib
    0.06
    ,而且
    0.06
    Activations Density 0.010%

    No Known Activations