© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69136
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash

    The neuron flags imperative or instructional verbs (e.g. “Prepare,” “Make,” “Give,” “Introduce”) in command-style user prompts.

    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
    ่าน
    -0.07
    adastrar
    -0.07
     boz
    -0.07
    13
    -0.06
    626
    -0.06
    643
    -0.06
     qb
    -0.06
     поперед
    -0.06
     podob
    -0.06
     coords
    -0.06
    POSITIVE LOGITS
    سين
    0.06
    $core
    0.06
    Authorities
    0.06
     Nation
    0.06
     grips
    0.06
     strerror
    0.06
    _LOADING
    0.06
     선택
    0.06
     facts
    0.06
    رق
    0.06
    Activations Density 0.012%

    No Known Activations