© 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. 7-RESID-POST-AA
    11. 97102
    Prev
    Next
    INDEX
    Explanations

    direction or movement

    np_max-act · gemini-2.0-flash

    the neuron detects phrasal verbs — verb + particle sequences (like "open up", "prints out", "lifting up").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gra
    -0.06
    身份
    -0.06
    proc
    -0.06
     Bro
    -0.06
     شاخ
    -0.06
    ko
    -0.06
    ึง
    -0.06
     clarification
    -0.06
     stroj
    -0.06
    groundColor
    -0.06
    POSITIVE LOGITS
     upon
    0.07
    ился
    0.07
     anim
    0.07
    色的
    0.06
    อเม
    0.06
    .topic
    0.06
     starting
    0.06
     Slack
    0.06
     wij
    0.06
    dál
    0.06
    Activations Density 0.360%

    No Known Activations