© 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. 11-RESID-POST-AA
    11. 17825
    Prev
    Next
    INDEX
    Explanations

    Diverse, mixed source texts

    np_max-act · gemini-2.0-flash

    statements of opinion or sentiment related to taste or preferences.

    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
    λω
    -0.07
     doubts
    -0.06
    (Function
    -0.06
     Ukr
    -0.06
     formato
    -0.06
     vocals
    -0.06
    丶
    -0.06
     TextField
    -0.06
    162
    -0.06
     سن
    -0.06
    POSITIVE LOGITS
    Methods
    0.07
     vegas
    0.06
    _cal
    0.06
    =[]
↵
    0.06
    gem
    0.06
    _down
    0.06
    غن
    0.06
    Sessions
    0.06
     Thy
    0.06
    ağa
    0.06
    Activations Density 0.069%

    No Known Activations