© 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. 109731
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of software frameworks.

    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
    Definition
    -0.07
    owntown
    -0.07
    _PORTS
    -0.06
    .remote
    -0.06
    submitted
    -0.06
     reminds
    -0.06
     cloned
    -0.06
     MAY
    -0.06
     May
    -0.06
    con
    -0.06
    POSITIVE LOGITS
     závod
    0.06
    !");
    ↵
    0.06
      
    ↵
    0.06
    沖
    0.06
     Müdür
    0.06
    ...
    ↵
    0.06
    іли
    0.06
    )}
    ↵
    0.06
    ้↵
    0.06
     :
    ↵
    0.06
    Activations Density 0.072%

    No Known Activations