© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91688
    Prev
    Next
    INDEX
    Explanations

    of how

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “mechanisms” (especially in phrases like “the mechanisms of …”).

    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
    .VisualBasic
    -0.08
     beetle
    -0.06
    	false
    -0.06
    880
    -0.06
     analytic
    -0.06
    aler
    -0.06
    woord
    -0.06
    False
    -0.06
     fatally
    -0.06
     witty
    -0.06
    POSITIVE LOGITS
    �
    0.07
     skup
    0.07
    nbr
    0.07
     seg
    0.06
     vatandaş
    0.06
     ssh
    0.06
    ground
    0.06
    .perm
    0.06
    (GET
    0.06
    /providers
    0.06
    Activations Density 0.061%

    No Known Activations