© 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. 30118
    Prev
    Next
    INDEX
    Explanations

    tests

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of testing practices or frameworks (e.g. “TDD,” “BDD,” “Test,” “tests,” “writing”).

    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
    IDAD
    -0.07
     UID
    -0.07
    할
    -0.06
    stk
    -0.06
    _CBC
    -0.06
    _RET
    -0.06
    _ACK
    -0.06
     Tome
    -0.06
     bidder
    -0.06
    _eng
    -0.06
    POSITIVE LOGITS
     Osw
    0.07
    €™
    0.07
    언
    0.06
    min
    0.06
    ////////
    0.06
    اتر
    0.06
     �
    0.06
    ğı
    0.06
    warf
    0.06
     effects
    0.06
    Activations Density 0.008%

    No Known Activations