© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 22329
    Prev
    Next
    INDEX
    Explanations

    Conversational writing/instructions

    np_max-act · gemini-2.0-flash

    Instances of direct second-person address (words and contractions that address the reader).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Antworten
    -0.07
     CVS
    -0.06
     ефектив
    -0.06
     bre
    -0.06
    esinin
    -0.06
    	FROM
    -0.06
    aste
    -0.06
    どう
    -0.06
    	offset
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Nachricht
    0.07
    Normalization
    0.07
     architects
    0.06
     Madrid
    0.06
    .visual
    0.06
     optimizations
    0.06
    [js
    0.06
    (savedInstanceState
    0.06
    -Agent
    0.06
     Czech
    0.06
    Activations Density 0.171%

    No Known Activations