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. 27027
    Prev
    Next
    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash

    The neuron activates on Italian past‐tense verb forms (particularly third-person plural imperfect or simple past endings like “erano,” “furono,” “divennero,” 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
     would
    -0.08
     Das
    -0.07
    aes
    -0.06
    ิงห
    -0.06
     Brands
    -0.06
    Fall
    -0.06
    ิเคราะห
    -0.06
     già
    -0.06
    .C
    -0.06
    HLT
    -0.06
    POSITIVE LOGITS
     كتب
    0.07
    {/*
    0.07
    된
    0.07
     urllib
    0.07
    ‌ش
    0.06
     alerted
    0.06
    ово
    0.06
    ouce
    0.06
     insider
    0.06
     Τζ
    0.06
    Activations Density 0.052%

    No Known Activations