© 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. 90840
    Prev
    Next
    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash

    The neuron activates on hexadecimal digits in “\uXXXX”‐style Unicode escape sequences.

    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
     tâm
    -0.08
     inter
    -0.07
     Mang
    -0.07
     Communication
    -0.07
     AIS
    -0.07
     S
    -0.07
    .Symbol
    -0.07
    -pattern
    -0.07
    _iteration
    -0.06
     diesel
    -0.06
    POSITIVE LOGITS
    getOption
    0.07
    _domains
    0.06
     exhibiting
    0.06
    ち
    0.06
     rn
    0.06
     Фед
    0.06
     coherence
    0.05
     다른
    0.05
    CCCCCC
    0.05
    arden
    0.05
    Activations Density 0.010%

    No Known Activations