© 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. 42979
    Prev
    Next
    INDEX
    Explanations

    hardship

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to being abused or a victim (e.g., “abused,” “abuse,” “victim”).

    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
     folder
    -0.07
    https
    -0.07
    HV
    -0.07
     mùi
    -0.07
    memory
    -0.06
     Epic
    -0.06
    .Users
    -0.06
     connected
    -0.06
    @
    -0.06
     concat
    -0.06
    POSITIVE LOGITS
    jet
    0.06
     Seas
    0.06
    -condition
    0.06
    iration
    0.06
    店
    0.06
    	View
    0.06
    ousel
    0.06
    .Platform
    0.06
    高校
    0.06
    .Span
    0.06
    Activations Density 0.134%

    No Known Activations