© 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. 124693
    Prev
    Next
    INDEX
    Explanations

    sharing thoughts/advice

    np_max-act · gemini-2.0-flash

    The neuron fires on ordinary lowercase content words in the main body of a post (common non‐proper, nonnumeric tokens) and remains off for headers, titles, names, dates, and punctuation.

    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
     Peggy
    -0.08
    очь
    -0.07
    GUI
    -0.07
     Liberties
    -0.06
    quisition
    -0.06
     Ranger
    -0.06
     Alternatively
    -0.06
     URI
    -0.06
    :Add
    -0.06
     pneumonia
    -0.06
    POSITIVE LOGITS
    [source
    0.07
    ůl
    0.06
    Um
    0.06
     lze
    0.06
     yasak
    0.06
    ]}>↵
    0.06
     explorer
    0.06
     güncel
    0.06
     -*-
    ↵
    0.06
     étaient
    0.06
    Activations Density 0.056%

    No Known Activations