© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128681
    Prev
    Next
    INDEX
    Explanations

    Code/Configuration snippets

    np_max-act · gemini-2.0-flash

    The neuron detects compiler preprocessor macro definitions (e.g. “-D…” or add_definitions/SET(…_VERSION “…”) flags) in build‐configuration files.

    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
     interchange
    -0.06
     souvenir
    -0.06
     Dickens
    -0.06
    =Y
    -0.06
    VIN
    -0.05
    .if
    -0.05
    evil
    -0.05
     withstand
    -0.05
     coined
    -0.05
    Standard
    -0.05
    POSITIVE LOGITS
    }".
    0.08
     LAB
    0.07
    <*
    0.07
     ostatní
    0.07
     좀
    0.07
     الأح
    0.07
     Crafting
    0.06
    lán
    0.06
    ..........
    0.06
    _control
    0.06
    Activations Density 0.008%

    No Known Activations