© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13022
    Prev
    Next
    INDEX
    Explanations

    Website forms/instructions

    np_max-act · gemini-2.0-flash

    The neuron fires on embedded HTML/form markup and related UI validation text within the document.

    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
     lovers
    -0.08
    질
    -0.07
     kuvvet
    -0.06
     KAR
    -0.06
     onemoc
    -0.06
     Olympia
    -0.06
    Monitor
    -0.06
     frogs
    -0.06
     dioxide
    -0.06
     Düny
    -0.06
    POSITIVE LOGITS
    ัดส
    0.06
     feasible
    0.06
    .TextAlignment
    0.06
    =$(
    0.06
     crews
    0.06
     snag
    0.06
     vale
    0.06
    (course
    0.06
    (cnt
    0.06
    (false
    0.06
    Activations Density 0.022%

    No Known Activations