© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108974
    Prev
    Next
    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash

    This neuron activates on the subordinating conjunction “when,” marking the start of conditional or temporal clauses.

    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
    .info
    -0.07
    ис
    -0.06
    著
    -0.06
     ON
    -0.06
     ([
    -0.06
     aquarium
    -0.06
    党
    -0.06
    號
    -0.06
    нообраз
    -0.06
    而
    -0.06
    POSITIVE LOGITS
    Nic
    0.07
     popover
    0.06
     Pence
    0.06
     dred
    0.06
    _allocated
    0.06
    -president
    0.06
    เพลง
    0.06
     smelled
    0.06
    toFloat
    0.06
    TestingModule
    0.06
    Activations Density 0.091%

    No Known Activations