© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89123
    Prev
    Next
    INDEX
    Explanations

    object .get

    np_max-act · gemini-2.0-flash

    code fragments related to reflection and generics in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on code tokens involving type inspection and reflection of generic classes (e.g. “Type,” “GetType,” “GenericArguments,” “isAssignableFrom,” etc.).

    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
    afx
    -0.06
     поб
    -0.06
     Outlook
    -0.06
    sofar
    -0.06
     acct
    -0.06
    accessToken
    -0.06
    言って
    -0.06
    Akt
    -0.06
     kadar
    -0.06
    olt
    -0.06
    POSITIVE LOGITS
     rentals
    0.08
    Step
    0.07
     "{
    0.07
    zę
    0.07
    =w
    0.07
    AH
    0.07
     loans
    0.07
     UserDefaults
    0.06
     stun
    0.06
    (conv
    0.06
    Activations Density 0.056%

    No Known Activations