© 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. 126786
    Prev
    Next
    INDEX
    Explanations

    Image

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the token “Image,” i.e. references to the PIL Image class/methods.

    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
     fileId
    -0.07
    .hstack
    -0.06
     GeForce
    -0.06
    وست
    -0.06
    пион
    -0.06
    ethoven
    -0.06
    지막
    -0.06
    ADI
    -0.06
    (textBox
    -0.06
    _VLAN
    -0.05
    POSITIVE LOGITS
    ibilities
    0.08
     Attached
    0.08
    负
    0.07
     Somerset
    0.07
    ุม
    0.07
    мами
    0.07
    -Out
    0.07
     uber
    0.07
    'We
    0.07
    igure
    0.07
    Activations Density 0.001%

    No Known Activations