Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54835
    Prev
    Next
    INDEX
    Explanations

    advice and opinions

    np_max-act · gemini-2.0-flash

    The neuron detects the start of the assistant’s alternative‐suggestion phrasing (e.g. “Instead, I suggest focusing on …”).

    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
    banks
    -0.07
    	stage
    -0.07
    억
    -0.07
    	base
    -0.07
    -St
    -0.06
    Python
    -0.06
    -inc
    -0.06
    GLOSS
    -0.06
     pret
    -0.06
    .answers
    -0.06
    POSITIVE LOGITS
     serviço
    0.07
     requests
    0.06
    .phi
    0.06
     reversing
    0.06
    icultural
    0.06
     unleashed
    0.06
    になり
    0.06
    。”↵↵
    0.06
    :black
    0.06
                
    0.06
    Activations Density 0.065%

    No Known Activations