© 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. 37059
    Prev
    Next
    INDEX
    Explanations

    mere

    np_max-act · gemini-2.0-flash

    text that contains elements of arrogance and manipulation, particularly in the context of power dynamics and relationships.

    oai_token-act-pair · gpt-4o-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
    ixon
    -0.07
    atl
    -0.06
    هایی
    -0.06
    -switch
    -0.06
    constitution
    -0.06
    яч
    -0.06
    ission
    -0.06
    áj
    -0.06
    ुकस
    -0.06
    ountain
    -0.06
    POSITIVE LOGITS
     merely
    0.14
     mere
    0.12
     Hoe
    0.08
    Modes
    0.07
    �
    0.07
    .createFrom
    0.07
     прост
    0.07
     bare
    0.07
    EUR
    0.07
     moderately
    0.07
    Activations Density 0.004%

    No Known Activations