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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 55385
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects square-bracketed labels (e.g. “[timing]”, “[test that summary]”, “[back trace]”, “[pre-back trace]”, “[path]”) in text.

    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
     tung
    -0.09
    -ce
    -0.06
     villagers
    -0.06
    acılık
    -0.06
    justice
    -0.06
    瓦
    -0.06
     Linden
    -0.06
    	gui
    -0.06
     Euros
    -0.06
    _signal
    -0.06
    POSITIVE LOGITS
    ={()
    0.07
     comunic
    0.06
    爭
    0.06
    					   
    0.06
     تحقیق
    0.06
    競
    0.06
    )";↵↵
    0.06
    :YES
    0.06
     تحصیل
    0.06
    習
    0.06
    Activations Density 0.012%

    No Known Activations