© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43345
    Prev
    Next
    INDEX
    Explanations

    Machiavelli and esters

    np_max-act · gemini-2.0-flash

    This neuron activates on the character sequence “av,” as found in names like “Machiavelli.”

    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
    üslü
    -0.06
    Put
    -0.06
    theid
    -0.06
     l
    -0.06
    IOC
    -0.06
     놀
    -0.06
    Ơ
    -0.06
    Evaluator
    -0.06
    ambah
    -0.06
    Bounding
    -0.06
    POSITIVE LOGITS
     Norway
    0.07
     circulating
    0.07
    ->{$
    0.07
    ¬
    0.06
     Liv
    0.06
    。」↵↵
    0.06
     RR
    0.06
    _lookup
    0.06
    	Spring
    0.06
    COOKIE
    0.06
    Activations Density 0.000%

    No Known Activations