© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125047
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron spotlights mentions of concrete services, facilities, or named features (e.g. “medical care,” “temples,” “vacation rentals,” “disorders”) in text.

    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
    ,c
    -0.06
     ip
    -0.06
    Snap
    -0.06
     rabbit
    -0.06
    Globals
    -0.06
     iphone
    -0.06
     football
    -0.06
     zenith
    -0.06
    セ
    -0.06
    Omega
    -0.05
    POSITIVE LOGITS
     fond
    0.07
     PF
    0.07
    년에
    0.07
    äm
    0.06
    ैठक
    0.06
    hoe
    0.06
     phê
    0.06
     ().
    0.06
    keletal
    0.06
     Persistent
    0.06
    Activations Density 0.378%

    No Known Activations