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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6660
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on fragments of URLs—especially query‐parameter keys, codes, and alphanumeric strings in web addresses.

    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
    /shared
    -0.07
     ])->
    -0.07
     Buccane
    -0.06
     شده
    -0.06
    .FIELD
    -0.06
     eps
    -0.06
     cannons
    -0.06
     داخل
    -0.06
     Granny
    -0.06
    paces
    -0.06
    POSITIVE LOGITS
     Sent
    0.07
    leans
    0.07
     Testament
    0.07
    èo
    0.06
    lili
    0.06
    _rc
    0.06
     Matte
    0.06
     envelop
    0.06
    elsing
    0.06
    typing
    0.06
    Activations Density 0.002%

    No Known Activations