© 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
    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. 68420
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron fires on the common negative‐prefix “un” (as in “unfortunately,” “united,” etc.).

    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
    ев
    -0.07
     Miranda
    -0.06
    ips
    -0.06
    603
    -0.06
    经验
    -0.06
    eman
    -0.06
     {%
    -0.06
     Isaiah
    -0.06
     goto
    -0.06
     Ward
    -0.06
    POSITIVE LOGITS
     $(".
    0.07
     клуб
    0.07
    rowad
    0.06
     settled
    0.06
     $('.
    0.06
    озмож
    0.06
    illary
    0.06
    -conf
    0.06
     glam
    0.06
    .ptr
    0.06
    Activations Density 0.026%

    No Known Activations