© 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. 66576
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    associations with language models that generate coherent and contextually relevant text.

    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
    eneral
    -0.07
    745
    -0.06
     getElement
    -0.06
     semester
    -0.06
     тепер
    -0.06
     ринку
    -0.06
    енту
    -0.06
     criterion
    -0.06
    跟
    -0.05
    ,buf
    -0.05
    POSITIVE LOGITS
     advancement
    0.07
    abaj
    0.07
    -login
    0.07
    oğan
    0.06
     Ende
    0.06
     LEFT
    0.06
     Instit
    0.06
    _cap
    0.06
     APPLICATION
    0.06
    osc
    0.06
    Activations Density 0.108%

    No Known Activations