© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13760
    Prev
    Next
    INDEX
    Explanations

    Case

    np_max-act · gemini-2.0-flash

    The neuron responds to isolated title-case or capitalized tokens (often the first word of a section or sentence).

    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
     객
    -0.07
    食
    -0.07
    _SF
    -0.06
     доб
    -0.06
     cour
    -0.06
    ब
    -0.06
    ':↵↵
    -0.06
    토토
    -0.06
     вред
    -0.06
    蜜
    -0.06
    POSITIVE LOGITS
    ıyorum
    0.07
     Defense
    0.07
    	typedef
    0.06
    .pad
    0.06
    ción
    0.06
     Bis
    0.06
    -enabled
    0.06
     Albums
    0.06
     knockout
    0.06
     NULL
    0.06
    Activations Density 0.356%

    No Known Activations