© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron detects in‐text reference/citation markers (e.g. “[ @ref … ]” with numeric citation values).

    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
     inertia
    -0.07
     nella
    -0.07
    going
    -0.07
    ariance
    -0.07
     Hao
    -0.07
     카지노
    -0.07
     poorest
    -0.06
     nodes
    -0.06
    rophic
    -0.06
     clockwise
    -0.06
    POSITIVE LOGITS
    дет
    0.06
    Ц
    0.06
    -defense
    0.06
     ],↵
    0.06
    QR
    0.06
     luder
    0.06
     somew
    0.06
    (G
    0.06
    หน
    0.06
    ieee
    0.06
    Activations Density 0.010%

    No Known Activations