© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90766
    Prev
    Next
    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash

    The neuron detects the use of SQL CASE expressions (especially in conditional aggregations).

    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
    .bind
    -0.07
     Malta
    -0.07
    بو
    -0.06
     Drupal
    -0.06
    "If
    -0.06
    LOOD
    -0.06
    Nuitka
    -0.06
    meteor
    -0.06
    _udp
    -0.06
     찬
    -0.06
    POSITIVE LOGITS
     O
    0.07
     notorious
    0.07
    room
    0.07
    Χ
    0.06
    ение
    0.06
    %A
    0.06
    -separated
    0.06
    _SEQUENCE
    0.06
     좋
    0.06
     extrem
    0.06
    Activations Density 0.001%

    No Known Activations