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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7331
    Prev
    Next
    INDEX
    Explanations

    technical compatibility

    np_max-act · gemini-2.0-flash

    The neuron fires on text discussing compatibility across different software (or data) versions.

    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
    Isl
    -0.06
    emies
    -0.06
    jury
    -0.06
    fault
    -0.06
    ()})↵
    -0.06
    bra
    -0.06
    BOOT
    -0.06
    EG
    -0.06
    Driver
    -0.06
    utation
    -0.06
    POSITIVE LOGITS
     обесп
    0.08
     sacrific
    0.07
    oralType
    0.07
     ContentValues
    0.07
     strs
    0.07
    ignKey
    0.06
     �
    0.06
    iosper
    0.06
     움직
    0.06
    лении
    0.06
    Activations Density 0.072%

    No Known Activations